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

    Neuronpedia

    INDEX
    Explanations

    size/count

    np_max-act · gemini-2.0-flash

    The neuron mainly responds to numeric literals (numbers and numeric constants) in the code.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    Materials
    -0.07
    .servlet
    -0.07
     marked
    -0.07
     наг
    -0.07
     جوان
    -0.07
    蕉
    -0.06
    Transport
    -0.06
     المه
    -0.06
    arakter
    -0.06
    Monday
    -0.06
    POSITIVE LOGITS
    ény
    0.07
    ;")↵
    0.07
    Č
    0.06
    CTYPE
    0.06
    UGHT
    0.06
     [...]
    0.06
     lex
    0.06
     Listen
    0.06
     Plant
    0.06
    �
    0.06
    Act Density 0.010%

    No Known Activations