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

    Neuronpedia

    INDEX
    Explanations

    questions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -mar
    -0.06
     آمد
    -0.06
     spanking
    -0.06
    FINE
    -0.06
    tí
    -0.06
     surfaced
    -0.06
     Zero
    -0.06
     Gordon
    -0.06
     Gall
    -0.06
    amar
    -0.06
    POSITIVE LOGITS
    стин
    0.07
    .setViewportView
    0.06
     IRequest
    0.06
    .Resize
    0.06
    .errorMessage
    0.06
    (ps
    0.06
     bureaucrats
    0.06
    iseum
    0.06
    Pose
    0.06
    ecd
    0.06
    Act Density 0.003%

    No Known Activations