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

    Neuronpedia

    INDEX
    Explanations

    ference

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     televizyon
    -0.07
    補
    -0.07
    posed
    -0.07
     Fot
    -0.06
    iat
    -0.06
     signIn
    -0.06
    iná
    -0.06
    727
    -0.06
     jet
    -0.06
    _co
    -0.06
    POSITIVE LOGITS
     pavement
    0.06
    (schema
    0.06
     misdemean
    0.06
    农业
    0.06
     Resolution
    0.06
    _SIGNATURE
    0.06
    ян
    0.06
    webkit
    0.06
     noexcept
    0.06
     آزمون
    0.06
    Act Density 0.001%

    No Known Activations