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

    Neuronpedia

    INDEX
    Explanations

    eve of holidays

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ルール
    0.70
    ری
    0.66
     January
    0.65
    アイデア
    0.65
    ри
    0.64
    ння
    0.64
    ルイ
    0.63
    اری
    0.62
     schimb
    0.62
    ツール
    0.61
    POSITIVE LOGITS
    ad
    0.82
    ,
    0.71
    es
    0.66
    heres
    0.66
    ↵
    0.63
    ush
    0.59
    berman
    0.59
    ants
    0.59
    ántica
    0.59
    s
    0.58
    Act Density 0.000%

    No Known Activations