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

    Neuronpedia

    INDEX
    Explanations

    en

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     CERT
    -0.06
    <data
    -0.06
     Occup
    -0.06
    (Current
    -0.06
    ла
    -0.06
     Innoc
    -0.06
     reflex
    -0.06
     Sicher
    -0.06
    _Label
    -0.06
     disadv
    -0.06
    POSITIVE LOGITS
    _stylesheet
    0.07
    >r
    0.07
    162
    0.06
     formulation
    0.06
     ao
    0.06
    .localScale
    0.06
    rung
    0.06
    :Set
    0.06
    o
    0.06
    -available
    0.06
    Act Density 0.001%

    No Known Activations