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

    Neuronpedia

    INDEX
    Explanations

    scientific abbreviations/symbols

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    /method
    -0.07
    record
    -0.07
    _then
    -0.07
     Deze
    -0.07
     �
    -0.07
    *((
    -0.07
    Exp
    -0.06
     Hicks
    -0.06
    .unlock
    -0.06
    First
    -0.06
    POSITIVE LOGITS
    isseur
    0.07
    زی
    0.07
    кат
    0.07
     ::
    0.06
     Says
    0.06
    بي
    0.06
     Associations
    0.06
    ležit
    0.06
     Rockefeller
    0.06
    ,'"
    0.06
    Act Density 0.098%

    No Known Activations