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

    Neuronpedia

    INDEX
    Explanations

    way to achieve

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ù
    0.44
    uales
    0.43
    и
    0.42
    uth
    0.42
    uuml
    0.40
     stesso
    0.40
     আঘাতে
    0.40
    ují
    0.39
     রক্তাক্ত
    0.39
    ulina
    0.38
    POSITIVE LOGITS
    了解到
    0.43
     obter
    0.40
    രിച്ചി
    0.39
     achieve
    0.39
     مطم
    0.39
    夙
    0.39
     manera
    0.39
     obtain
    0.38
    を実現
    0.38
     introduce
    0.38
    Act Density 0.113%

    No Known Activations