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

    Neuronpedia

    INDEX
    Explanations

    uniqueness

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -inf
    -0.07
    kJ
    -0.06
     COPY
    -0.06
    .Adapter
    -0.06
    oài
    -0.06
    _=
    -0.06
     Timothy
    -0.06
     orc
    -0.06
     "=
    -0.06
     Kad
    -0.06
    POSITIVE LOGITS
    ugs
    0.07
    .sms
    0.06
     तरह
    0.06
    FlatButton
    0.06
    using
    0.06
     в
    0.06
    .unknown
    0.06
     underestimated
    0.06
    ��
    0.06
     RANGE
    0.06
    Act Density 0.005%

    No Known Activations