Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    are

    np_max-act · gemini-2.0-flash

    phrases related to causes or factors associated with a specific condition or symptom.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    The neuron lights up on the little function words—auxiliary verbs (do, are) and prepositions (through, for)—that immediately follow “What” in a question, marking the structure of interrogative phrases.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Bates
    -0.07
    TABLE
    -0.07
    (head
    -0.06
     Core
    -0.06
    .order
    -0.06
     recovery
    -0.06
     ERROR
    -0.06
    &m
    -0.06
    .border
    -0.06
     CROSS
    -0.06
    POSITIVE LOGITS
    사가
    0.09
     });↵↵↵↵
    0.07
     GUIDATA
    0.07
     olarak
    0.07
    unun
    0.06
    ()))
↵
    0.06
    ırı
    0.06
    ประช
    0.06
    rát
    0.06
    ़ें
    0.06
    Act Density 0.256%

    No Known Activations