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

    Neuronpedia

    INDEX
    Explanations

    dates and numbers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    0
    0.50
    ence
    0.49
    is
    0.45
    ahrer
    0.41
    9
    0.41
    itej
    0.40
    2
    0.40
    ir
    0.39
    ０
    0.39
    4
    0.38
    POSITIVE LOGITS
     belliger
    0.43
     پوچھا
    0.41
    ✤
    0.40
     missp
    0.40
    を見て
    0.39
     கேள்வி
    0.38
    <unused377>
    0.38
     trailbl
    0.38
     compt
    0.38
     ڈی
    0.38
    Act Density 0.007%

    No Known Activations