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

    Neuronpedia

    INDEX
    Explanations

    understanding of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     bội
    0.41
    ूले
    0.41
    ष्ठा
    0.40
     activité
    0.40
    父
    0.38
     ചേ
    0.37
     Treasure
    0.37
    ரா
    0.37
    missible
    0.37
    нде
    0.36
    POSITIVE LOGITS
     явля
    0.44
    {"
    0.41
     etmektedir
    0.39
     ஹை
    0.38
    window
    0.38
    Ses
    0.37
     Jail
    0.36
    되었습니다
    0.36
    Carolina
    0.36
    தமிழ்
    0.35
    Act Density 0.001%

    No Known Activations