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

    Neuronpedia

    INDEX
    Explanations

    and

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Joy
    -0.08
     Powder
    -0.07
     TODAY
    -0.07
     rotational
    -0.07
     Carnegie
    -0.07
     fois
    -0.06
    But
    -0.06
    IZED
    -0.06
    Status
    -0.06
     But
    -0.06
    POSITIVE LOGITS
    ือถ
    0.07
    ชาย
    0.06
     anon
    0.06
    took
    0.06
    /Image
    0.06
    _ulong
    0.06
     Brasil
    0.06
    랜
    0.06
     Icelandic
    0.06
    /hooks
    0.06
    Act Density 0.054%

    No Known Activations