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

    Neuronpedia

    INDEX
    Explanations

    finds all, highlight the

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    และการ
    0.50
     takich
    0.40
    वेळी
    0.39
     також
    0.39
     کامیاب
    0.39
     daca
    0.39
    밌
    0.38
     друз
    0.38
    和服务
    0.38
     таксама
    0.38
    POSITIVE LOGITS
     the
    0.47
     in
    0.43
     from
    0.43
    the
    0.43
    [
    0.42
     approximately
    0.41
     on
    0.41
    (
    0.38
         
    0.38
    {\
    0.38
    Act Density 0.319%

    No Known Activations