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

    Neuronpedia

    INDEX
    Explanations

    {

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     diagnosed
    -0.07
     unic
    -0.07
     Enc
    -0.07
     Sure
    -0.06
     carga
    -0.06
     Pal
    -0.06
     Ind
    -0.06
    FILENAME
    -0.06
     Painter
    -0.06
    _game
    -0.06
    POSITIVE LOGITS
    زام
    0.07
    )、
    0.06
     سخت
    0.06
    cular
    0.06
    rank
    0.06
     �
    0.06
     домов
    0.06
     багатьох
    0.06
    ्थल
    0.06
     examination
    0.06
    Act Density 0.003%

    No Known Activations