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

    Neuronpedia

    INDEX
    Explanations

    anti-

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    見る
    0.41
    Há
    0.41
    用户
    0.40
    Differences
    0.39
    ложи
    0.39
     `<`,
    0.38
    ⤠
    0.38
    저
    0.38
     डिमांड
    0.37
    водится
    0.37
    POSITIVE LOGITS
     anti
    1.06
     анти
    0.98
     ant
    0.95
     antis
    0.93
     Anti
    0.91
     antip
    0.91
     एंटी
    0.89
     ANTI
    0.87
    Anti
    0.86
     antif
    0.85
    Act Density 0.033%

    No Known Activations