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

    Neuronpedia

    INDEX
    Explanations

    explanation of changes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ar
    0.46
    ல்கள்
    0.42
    rowning
    0.39
    क्टेयर
    0.39
    дит
    0.39
    ur
    0.39
    ]):
    0.39
    ございます
    0.39
     σημ
    0.38
     gentle
    0.38
    POSITIVE LOGITS
    방법
    0.51
     qued
    0.50
    사람
    0.48
     sortes
    0.47
    metry
    0.47
     commerciale
    0.47
     Explosion
    0.46
    삶
    0.46
     diferentes
    0.46
     طرق
    0.45
    Act Density 0.004%

    No Known Activations