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

    Neuronpedia

    INDEX
    Explanations

    rel

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .Single
    -0.07
     στι
    -0.07
    γχ
    -0.06
    mıştır
    -0.06
    "Our
    -0.06
    Suc
    -0.06
     Adult
    -0.06
     콘
    -0.06
    应该
    -0.06
     Combination
    -0.06
    POSITIVE LOGITS
     наруш
    0.07
    دواج
    0.06
     druž
    0.06
    uld
    0.06
     pige
    0.06
    .Dispose
    0.06
     setHidden
    0.06
    (send
    0.06
    setVisible
    0.06
    _cn
    0.06
    Act Density 0.001%

    No Known Activations