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

    Neuronpedia

    INDEX
    Explanations

    foreign language or script

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    /
    0.46
    ’
    0.41
     and
    0.36
     bzw
    0.35
     What
    0.34
    0.34
     যেসব
    0.33
     or
    0.32
     n
    0.32
    n
    0.31
    POSITIVE LOGITS
     देम
    0.48
     עם
    0.39
    ת
    0.39
    ི
    0.38
    نګ
    0.36
    𒊑
    0.36
    יי
    0.35
    戽
    0.35
    ກັບ
    0.35
    ୮
    0.35
    Act Density 0.315%

    No Known Activations