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

    Neuronpedia

    INDEX
    Explanations

    code, data, and time

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    toolbox
    -0.07
    oria
    -0.07
    ặng
    -0.06
    adh
    -0.06
    icense
    -0.06
    odelist
    -0.06
    /*.
    -0.06
    handles
    -0.06
    _connector
    -0.06
     Tracks
    -0.06
    POSITIVE LOGITS
     города
    0.07
    Population
    0.06
     legislators
    0.06
    -Trump
    0.06
    ูปแบบ
    0.06
     فاصله
    0.06
     ViewHolder
    0.06
    pragma
    0.06
     tirelessly
    0.06
    ıntı
    0.06
    Act Density 0.018%

    No Known Activations