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

    Neuronpedia

    INDEX
    Explanations

    Red Man

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Wind
    0.46
    撸
    0.39
     Осно
    0.39
     Arach
    0.38
     Bucc
    0.36
     автоном
    0.36
     风
    0.35
    NAMES
    0.35
     основании
    0.35
    Kh
    0.34
    POSITIVE LOGITS
     obscur
    0.43
    ಜೆ
    0.42
     ip
    0.41
     sequ
    0.40
    נדה
    0.40
    ثله
    0.38
     simpat
    0.38
     attendre
    0.38
     Majka
    0.38
    لقة
    0.37
    Act Density 0.002%

    No Known Activations