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

    Neuronpedia

    INDEX
    Explanations

    be anyway

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ঃ
    0.36
     nuov
    0.33
     түр
    0.31
     affiche
    0.31
    0.31
     Antennes
    0.31
     ফ
    0.30
     LABEL
    0.30
     ಹಾಗೂ
    0.30
     രാഷ്ട്രീയ
    0.29
    POSITIVE LOGITS
    ola
    0.31
    iat
    0.30
    iaz
    0.30
    .“
    0.29
    you
    0.29
    ard
    0.29
     делать
    0.29
    ?’
    0.28
    ievable
    0.28
    ?
    0.28
    Act Density 0.000%

    No Known Activations