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
     Administration
    -0.07
     Gu
    -0.06
    Sessions
    -0.06
     var
    -0.06
     Brooklyn
    -0.06
    $product
    -0.06
     um
    -0.06
     refine
    -0.06
     DOJ
    -0.06
     vaccination
    -0.06
    POSITIVE LOGITS
     smě
    0.08
    ोग
    0.07
    fresh
    0.07
     tisí
    0.07
    複
    0.06
    كور
    0.06
     nuôi
    0.06
    orida
    0.06
    ща
    0.06
     té
    0.06
    Act Density 0.002%

    No Known Activations