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

    Neuronpedia

    INDEX
    Explanations

    dates and times

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ↵↵
    0.57
     coding
    0.52
    编码
    0.47
     estet
    0.45
     as
    0.45
    δε
    0.45
    راً
    0.44
    推
    0.44
    در
    0.44
    联
    0.44
    POSITIVE LOGITS
    ಟ್
    0.53
    selfobj
    0.51
    hunters
    0.48
     ਰ
    0.48
     لئے
    0.48
     ファイル
    0.47
     فائلوں
    0.47
    retval
    0.47
     vinos
    0.46
    farm
    0.46
    Act Density 0.000%

    No Known Activations