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

    Neuronpedia

    INDEX
    Explanations

    Place names

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (Py
    -0.08
     ip
    -0.07
    ()),
    -0.07
    .High
    -0.07
    .in
    -0.07
     onHide
    -0.07
     aquarium
    -0.07
    וה
    -0.07
     multipart
    -0.07
    _D
    -0.07
    POSITIVE LOGITS
     kW
    0.07
    开具
    0.07
    找回
    0.07
    mo
    0.06
    ืน
    0.06
    귿
    0.06
    .ErrorMessage
    0.06
    万亿元
    0.06
     отзыв
    0.06
    BREAK
    0.06
    Act Density 0.144%

    No Known Activations