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

    Neuronpedia

    INDEX
    Explanations

    say "operator"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Farm
    -0.07
     inventor
    -0.07
    ете
    -0.07
    adapt
    -0.07
     flirting
    -0.06
    pageNumber
    -0.06
    нт
    -0.06
    _arguments
    -0.06
    alertView
    -0.06
    输出
    -0.06
    POSITIVE LOGITS
     dla
    0.06
    hai
    0.06
     widening
    0.06
    loys
    0.06
     facile
    0.06
     aaa
    0.06
     Pří
    0.06
     toplam
    0.06
     jinak
    0.05
     derives
    0.05
    Act Density 0.051%

    No Known Activations