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

    Neuronpedia

    INDEX
    Explanations

    JSON structures

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ﺍ
    0.50
    RAchievement
    0.49
    <bos>
    0.49
     söyled
    0.47
     Pharisees
    0.46
     मुआव
    0.44
    Ṕ
    0.44
    Alpes
    0.44
    நீங்கள்
    0.44
    ljen
    0.44
    POSITIVE LOGITS
    和
    0.42
     to
    0.41
     of
    0.41
    <code>
    0.41
     was
    0.41
    它
    0.41
     satir
    0.40
    1
    0.39
     ਦੀ
    0.39
    的
    0.39
    Act Density 0.016%

    No Known Activations