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

    Neuronpedia

    INDEX
    Explanations

    format

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .apply
    -0.07
    ão
    -0.07
    Actions
    -0.07
    .Orientation
    -0.06
     뛰
    -0.06
     �
    -0.06
     Monsters
    -0.06
    物理
    -0.06
     ngay
    -0.06
    imators
    -0.06
    POSITIVE LOGITS
    DIV
    0.07
     bal
    0.06
     rsp
    0.06
    logger
    0.06
     ذ
    0.06
     Bal
    0.06
    дел
    0.06
     Mc
    0.06
     Dependencies
    0.06
    ERM
    0.06
    Act Density 0.010%

    No Known Activations