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

    Neuronpedia

    INDEX
    Explanations

    undressing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Aless
    -0.07
    EditText
    -0.07
     آورد
    -0.06
     savage
    -0.06
     Mec
    -0.06
     Shak
    -0.06
    _bot
    -0.06
     thematic
    -0.06
     Regulation
    -0.06
    �
    -0.06
    POSITIVE LOGITS
    .Branch
    0.07
    (handler
    0.07
    curve
    0.07
    .Microsoft
    0.07
     vd
    0.06
     "-
    0.06
     обычно
    0.06
    )를
    0.06
    unction
    0.06
    جاد
    0.06
    Act Density 0.009%

    No Known Activations