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

    Neuronpedia

    INDEX
    Explanations

    Web searches or turning up

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     writes
    -0.07
     media
    -0.07
    kich
    -0.07
    .En
    -0.06
    陵
    -0.06
     interior
    -0.06
     profile
    -0.06
    block
    -0.06
    Guy
    -0.06
     Martins
    -0.06
    POSITIVE LOGITS
    上が
    0.07
    送料無料
    0.07
     عند
    0.07
     زیب
    0.07
    _ITER
    0.06
     반
    0.06
    _Call
    0.06
    /mail
    0.06
    .querySelectorAll
    0.06
     Украї
    0.06
    Act Density 0.062%

    No Known Activations