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

    Neuronpedia

    INDEX
    Explanations

    packed

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     CNBC
    -0.06
     Pulse
    -0.06
    -off
    -0.06
     Torah
    -0.06
    veloper
    -0.06
     Под
    -0.06
    HD
    -0.06
     Brigade
    -0.06
     подраз
    -0.06
    itbart
    -0.06
    POSITIVE LOGITS
     sincerely
    0.07
     erot
    0.07
     -=
    0.07
    ）（
    0.07
     město
    0.07
    �
    0.07
     packed
    0.07
    าการ
    0.06
     NaN
    0.06
    _tokenize
    0.06
    Act Density 0.008%

    No Known Activations