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

    Neuronpedia

    INDEX
    Explanations

    articles and prepositions

    np_max-act · gemini-2.0-flash

    The neuron is sensitive to floating‐point numeric tokens, i.e. decimal numbers.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     subconscious
    -0.06
     parents
    -0.06
    เลข
    -0.06
    Analyzer
    -0.06
     Conscious
    -0.06
    competitive
    -0.06
     Suzanne
    -0.06
     Hük
    -0.06
    ερ
    -0.06
    -heart
    -0.06
    POSITIVE LOGITS
    방송
    0.08
     Olymp
    0.08
     Assy
    0.06
    ymbol
    0.06
     нали
    0.06
     Alo
    0.06
    .StackTrace
    0.06
     короб
    0.06
    IGINAL
    0.06
     뉴
    0.06
    Act Density 0.019%

    No Known Activations