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

    Neuronpedia

    INDEX
    Explanations

    large quantities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    on
    0.87
    L
    0.86
    A
    0.82
    il
    0.79
    φέρει
    0.78
    و
    0.77
    ptic
    0.75
    ду
    0.73
    scorer
    0.73
    ו
    0.72
    POSITIVE LOGITS
    لي
    1.05
    .
    0.91
    たくさん
    0.91
     informacije
    0.87
    信息
    0.80
    เหมือน
    0.80
    很多
    0.79
    ");
    0.79
    亚洲
    0.78
    的相关
    0.76
    Act Density 0.386%

    No Known Activations