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

    Neuronpedia

    INDEX
    Explanations

    shortening

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    pii
    -0.06
    に出
    -0.06
     calendar
    -0.06
     couples
    -0.06
    @Slf
    -0.06
    lexical
    -0.06
     nominate
    -0.06
     panties
    -0.06
    POWER
    -0.06
     caract
    -0.06
    POSITIVE LOGITS
    -strip
    0.08
    SH
    0.08
     SH
    0.08
    PRI
    0.07
    svp
    0.06
    .BorderStyle
    0.06
     storytelling
    0.06
     PRI
    0.06
     thuộc
    0.06
    expected
    0.06
    Act Density 0.009%

    No Known Activations