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

    Neuronpedia

    INDEX
    Explanations

    Dashes and parentheses

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     keras
    -0.07
    protected
    -0.06
    telephone
    -0.06
    ometrics
    -0.06
     epit
    -0.06
     distributed
    -0.06
    anked
    -0.06
    推
    -0.06
    ynomials
    -0.05
     arrives
    -0.05
    POSITIVE LOGITS
    圈
    0.07
    _MUT
    0.07
    無
    0.07
     terör
    0.07
     chave
    0.07
    BI
    0.07
    (EIF
    0.07
    ARD
    0.07
    ');↵↵↵
    0.07
    WA
    0.06
    Act Density 0.068%

    No Known Activations