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

    Neuronpedia

    INDEX
    Explanations

    long condition

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     jednego
    0.55
    orschungs
    0.43
     μεγά
    0.42
    ایت
    0.41
     Grandes
    0.39
     każdego
    0.38
     algodón
    0.38
     jedno
    0.37
     duż
    0.37
     nörd
    0.37
    POSITIVE LOGITS
     conveniences
    0.36
    ಿಕ್
    0.35
    ’
    0.35
     did
    0.34
    ivam
    0.34
     छो
    0.34
     પાસે
    0.34
    ᅴ
    0.34
    io
    0.33
     eigenvector
    0.33
    Act Density 0.123%

    No Known Activations