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

    Neuronpedia

    INDEX
    Explanations

    mathematical language and discussions of logic

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    709
    -0.06
    945
    -0.06
    _equals
    -0.06
    acomment
    -0.06
    oho
    -0.06
    704
    -0.06
    _fu
    -0.06
    ancel
    -0.06
    åĿļ
    -0.06
    oodles
    -0.06
    POSITIVE LOGITS
    ï¼īãģ¯
    0.10
    ")!=
    0.09
    ")==
    0.09
    "is
    0.08
    åŃIJãģ¯
    0.08
    ì§ĢëĬĶ
    0.08
     seems
    0.08
     may
    0.07
    chas
    0.07
    )ìĿĢ
    0.07
    Act Density 0.256%

    No Known Activations