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

    Neuronpedia

    INDEX
    Explanations

    actions or events

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    sie
    -0.08
    ูล
    -0.07
    เขา
    -0.07
    Eff
    -0.07
     Öğ
    -0.07
     defender
    -0.06
    енного
    -0.06
    IL
    -0.06
     підт
    -0.06
     učitel
    -0.06
    POSITIVE LOGITS
     Aleppo
    0.07
    )<
    0.06
     dimension
    0.06
    dana
    0.06
    }<
    0.06
     exposing
    0.06
    (script
    0.06
     onward
    0.06
    (QL
    0.06
    	header
    0.06
    Act Density 0.136%

    No Known Activations