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
    _XML
    -0.08
    ?’
    -0.07
    ?[
    -0.06
     dreadful
    -0.06
     Yar
    -0.06
    تو
    -0.06
     estimate
    -0.06
    ホ
    -0.06
    ुश
    -0.06
    .className
    -0.06
    POSITIVE LOGITS
     переб
    0.07
     позвол
    0.07
     erotik
    0.07
    ("
    0.07
    mani
    0.06
     BF
    0.06
     superf
    0.06
    .but
    0.06
    ",
    0.06
     أيضا
    0.06
    Act Density 0.170%

    No Known Activations