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

    Neuronpedia

    INDEX
    Explanations

    certify

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -select
    -0.07
    Allow
    -0.07
    Viol
    -0.06
     Instance
    -0.06
    Ι
    -0.06
     glo
    -0.06
     seizing
    -0.06
     seab
    -0.06
    .He
    -0.06
    ablo
    -0.06
    POSITIVE LOGITS
    .cleanup
    0.07
    cej
    0.07
    odigo
    0.07
     fecha
    0.06
    _WIFI
    0.06
    тон
    0.06
    아이
    0.06
     roky
    0.06
     Dietary
    0.06
    alink
    0.06
    Act Density 0.003%

    No Known Activations