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

    Neuronpedia

    INDEX
    Explanations

    overall summary

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    0.73
    ursing
    0.66
    ä
    0.66
     construir
    0.65
     orifices
    0.63
     varje
    0.63
    brahim
    0.62
     Comes
    0.61
     pauses
    0.61
    ’!
    0.61
    POSITIVE LOGITS
    డు
    0.66
    ية
    0.65
    书
    0.60
    וק
    0.59
     bądź
    0.57
    יו
    0.56
    考えると
    0.56
    يل
    0.56
    in
    0.55
    يب
    0.55
    Act Density 0.173%

    No Known Activations