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

    Neuronpedia

    INDEX
    Explanations

    code or data snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    坚
    -0.06
     людям
    -0.06
    sciously
    -0.06
    ститут
    -0.06
    алеж
    -0.06
    ไร
    -0.06
     základě
    -0.06
    ožná
    -0.06
    .btnExit
    -0.06
     труб
    -0.06
    POSITIVE LOGITS
    568
    0.07
    /color
    0.06
    ,file
    0.06
     Heritage
    0.06
    mg
    0.06
    Textarea
    0.06
     imprisonment
    0.06
    ुप
    0.06
     legion
    0.06
     استاند
    0.06
    Act Density 0.000%

    No Known Activations