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
     celle
    -0.07
    :n
    -0.06
    allet
    -0.06
    IALIZ
    -0.06
    nelle
    -0.06
     Xia
    -0.06
     titul
    -0.06
    уд
    -0.06
     如果
    -0.06
    .Atomic
    -0.06
    POSITIVE LOGITS
     threatens
    0.07
    .stringValue
    0.07
     HOR
    0.07
     behaved
    0.06
     threaten
    0.06
     hearing
    0.06
    <ActionResult
    0.06
    PO
    0.06
    _WS
    0.06
    	effect
    0.06
    Act Density 0.002%

    No Known Activations