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

    Neuronpedia

    INDEX
    Explanations

    ZIP file

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ர்ஸ்
    0.42
     javax
    0.42
    ကြောင့်
    0.42
    שית
    0.41
     *}\
    0.40
    JPanel
    0.39
     BEING
    0.39
    extrémité
    0.39
     chłop
    0.39
    queryString
    0.39
    POSITIVE LOGITS
     charla
    0.41
     personal
    0.38
     growths
    0.37
     casado
    0.35
    送
    0.35
     vision
    0.35
     NPC
    0.35
     За
    0.35
     ввод
    0.35
     polynomial
    0.34
    Act Density 0.000%

    No Known Activations