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
     spine
    -0.07
     उन
    -0.06
     brunch
    -0.06
     предмет
    -0.06
    ूं
    -0.06
    odka
    -0.06
     kayak
    -0.06
     sexo
    -0.06
     Subway
    -0.06
     Володими
    -0.06
    POSITIVE LOGITS
    html
    0.07
     relieved
    0.06
    min
    0.06
    Letters
    0.06
     sewing
    0.06
    below
    0.06
    �州
    0.06
    (vector
    0.06
     prohibiting
    0.06
    ственные
    0.06
    Act Density 0.008%

    No Known Activations