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

    Neuronpedia

    INDEX
    Explanations

    trades and services

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     použ
    0.38
    ز
    0.38
     suono
    0.36
    音樂
    0.35
     ().
    0.35
     hebben
    0.34
     மொழ
    0.34
    ও
    0.34
     გამოყენ
    0.33
    聲音
    0.32
    POSITIVE LOGITS
    t
    0.52
    c
    0.52
    x
    0.48
    an
    0.47
    ta
    0.46
    ad
    0.43
    tails
    0.43
    tors
    0.43
    tas
    0.41
    k
    0.41
    Act Density 0.060%

    No Known Activations