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

    Neuronpedia

    INDEX
    Explanations

    .

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     член
    -0.06
     swapping
    -0.06
    .wait
    -0.06
    finite
    -0.06
    .Cancel
    -0.06
    .Failure
    -0.06
    .Scope
    -0.06
    culated
    -0.06
    (wx
    -0.06
    Ship
    -0.06
    POSITIVE LOGITS
    ồ
    0.07
    mploy
    0.07
     श
    0.06
    ulmuş
    0.06
    802
    0.06
    ứt
    0.06
    Под
    0.06
     calidad
    0.06
     bluff
    0.06
    eq
    0.06
    Act Density 0.013%

    No Known Activations