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

    Neuronpedia

    INDEX
    Explanations

    corresponding

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    /all
    -0.06
    libft
    -0.06
     alanda
    -0.06
     Robertson
    -0.06
    _fg
    -0.06
     albums
    -0.06
     Jal
    -0.06
    WORK
    -0.06
     мет
    -0.05
    _ra
    -0.05
    POSITIVE LOGITS
     orthodox
    0.07
    ↵
    0.07
    ¯¯¯¯
    0.07
    گاهی
    0.07
     пораж
    0.07
     embarrass
    0.07
    0.07
    loys
    0.07
     nonzero
    0.06
    ovenant
    0.06
    Act Density 0.008%

    No Known Activations