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

    Neuronpedia

    INDEX
    Explanations

    a

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     aktu
    -0.07
    ancellationToken
    -0.07
     QT
    -0.06
    .FLAG
    -0.06
    ーナ
    -0.06
     Haus
    -0.06
     queen
    -0.06
     antagonist
    -0.06
    _study
    -0.06
    GI
    -0.06
    POSITIVE LOGITS
    plement
    0.06
    Edward
    0.06
    announce
    0.06
    requ
    0.06
     nông
    0.06
     wrestling
    0.06
    wick
    0.06
    elix
    0.06
    lf
    0.06
     ابو
    0.06
    Act Density 0.000%

    No Known Activations