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

    Neuronpedia

    INDEX
    Explanations

    code, integer types

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    =$('#
    -0.08
     Checkbox
    -0.07
    _overlap
    -0.07
    .TextUtils
    -0.07
     strconv
    -0.07
     كافة
    -0.07
     PendingIntent
    -0.07
    ⤶
    -0.07
    'ils
    -0.07
     ITEMS
    -0.07
    POSITIVE LOGITS
    โร
    0.08
     pai
    0.07
     equilibrium
    0.07
    サラ
    0.07
    �
    0.07
    盉
    0.06
    长辈
    0.06
    洁
    0.06
    _decision
    0.06
     symbol
    0.06
    Act Density 0.014%

    No Known Activations