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

    Neuronpedia

    INDEX
    Explanations

    over time, for every

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     during
    0.46
     During
    0.45
    今後
    0.45
    на
    0.43
    уд
    0.42
    During
    0.41
    during
    0.41
     devenit
    0.41
    चणी
    0.41
    ات
    0.40
    POSITIVE LOGITS
     superstar
    0.44
    īng
    0.42
     extraordinary
    0.41
     μη
    0.41
     безопасности
    0.40
    relativePath
    0.40
     unexpected
    0.39
     bestimmten
    0.39
     جھ
    0.39
    ჯგუფი
    0.39
    Act Density 0.003%

    No Known Activations