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

    Neuronpedia

    INDEX
    Explanations

    class

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    IMENT
    -0.07
     refers
    -0.07
    (datetime
    -0.07
    、中
    -0.06
    _bal
    -0.06
    oca
    -0.06
     dumped
    -0.06
     jej
    -0.06
     să
    -0.06
    <pre
    -0.06
    POSITIVE LOGITS
     juvenile
    0.06
    _BASIC
    0.06
    "]->
    0.06
     Denis
    0.06
    eten
    0.06
    ymbols
    0.06
    ショ
    0.06
    ωση
    0.06
    uden
    0.06
    pras
    0.06
    Act Density 0.003%

    No Known Activations