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

    Neuronpedia

    INDEX
    Explanations

    Inaction and indifference

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ันเป
    -0.07
    拍
    -0.07
    �
    -0.06
    �
    -0.06
     Cho
    -0.06
    MODE
    -0.06
     hefty
    -0.06
    ｛
    -0.06
    лед
    -0.06
     Stud
    -0.06
    POSITIVE LOGITS
     uint
    0.06
     ceiling
    0.06
    ,proto
    0.06
     asset
    0.06
    ipel
    0.06
    ,int
    0.06
    _Helper
    0.06
     junior
    0.06
    .role
    0.06
     textarea
    0.06
    Act Density 0.016%

    No Known Activations