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

    Neuronpedia

    INDEX
    Explanations

    IT followed by industry terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ओं
    0.61
    ාවිත
    0.59
    تری
    0.53
     ﺍﻟ
    0.52
    その
    0.51
     ٣
    0.50
     Ат
    0.49
     Рим
    0.49
    Ⲃ
    0.49
     potência
    0.49
    POSITIVE LOGITS
    <0x80>
    0.84
    an
    0.84
    O
    0.75
    c
    0.73
    0
    0.70
    ',
    0.66
    f
    0.65
    K
    0.65
    A
    0.64
     IT
    0.63
    Act Density 0.005%

    No Known Activations