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

    Neuronpedia

    INDEX
    Explanations

    example followed by punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     neuroscience
    0.80
    ...",
    0.75
    ोटा
    0.73
     ...,
    0.71
    羣
    0.70
     truth
    0.69
     লেখা
    0.69
     !",
    0.69
     struggling
    0.69
     ",
    0.69
    POSITIVE LOGITS
    ,
    0.99
    ،
    0.92
    ,-
    0.92
    гӀ
    0.79
    нибудь
    0.78
    ,-\
    0.73
    ấp
    0.71
    влено
    0.70
    ,(
    0.69
    otification
    0.69
    Act Density 0.152%

    No Known Activations