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

    Neuronpedia

    INDEX
    Explanations

    short strings TTS

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ний
    0.49
    staben
    0.47
    s
    0.44
    usive
    0.43
    yya
    0.42
    atr
    0.42
    aw
    0.41
     Ive
    0.41
    ani
    0.41
    чих
    0.41
    POSITIVE LOGITS
     COMPLEXES
    0.48
     tổn
    0.48
    ্যান্ড
    0.47
     tĩnh
    0.47
    캠
    0.46
     नारे
    0.46
    形成的
    0.46
    编
    0.46
     lágrimas
    0.45
    碳
    0.45
    Act Density 0.000%

    No Known Activations