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

    Neuronpedia

    INDEX
    Explanations

    cd

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Trip
    -0.07
    NIC
    -0.07
    aviour
    -0.07
     anni
    -0.06
     mommy
    -0.06
     contentView
    -0.06
    eníze
    -0.06
    esp
    -0.06
     فول
    -0.06
    chio
    -0.06
    POSITIVE LOGITS
    ـــ
    0.06
     Gilbert
    0.06
     performs
    0.06
     두
    0.06
     개인
    0.06
    meli
    0.06
     anzeigen
    0.06
    (util
    0.06
    /mol
    0.06
     Luis
    0.06
    Act Density 0.002%

    No Known Activations