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

    Neuronpedia

    INDEX
    Explanations

    See

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _fake
    -0.08
    itespace
    -0.07
    backgroundColor
    -0.07
    disconnect
    -0.07
     ignoring
    -0.06
    toISOString
    -0.06
    atica
    -0.06
    imum
    -0.06
     modification
    -0.06
    変
    -0.06
    POSITIVE LOGITS
    	an
    0.06
     मध
    0.06
    .an
    0.06
    istrovství
    0.06
     至
    0.06
    .&
    0.06
     stě
    0.06
     eğit
    0.06
    _EC
    0.06
     authenticated
    0.06
    Act Density 0.004%

    No Known Activations