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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    manuel
    -0.07
    passport
    -0.07
     muscular
    -0.07
     bénéficie
    -0.07
    🏡
    -0.07
    本赛季
    -0.07
    Posted
    -0.07
    _CANCEL
    -0.07
    USART
    -0.06
     +↵↵
    -0.06
    POSITIVE LOGITS
    ref
    0.07
    eh
    0.07
    堅
    0.07
     Destroy
    0.06
    可靠的
    0.06
     alc
    0.06
     tah
    0.06
    TEGR
    0.06
     irq
    0.06
    ech
    0.06
    Act Density 0.036%

    No Known Activations