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

    Neuronpedia

    INDEX
    Explanations

    books and writing style

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ラー
    0.43
    cional
    0.42
     önemlidir
    0.42
    änge
    0.40
    ्युनिटी
    0.40
    ристи
    0.38
    骊
    0.36
    ক্তিক
    0.36
    люби
    0.35
    онер
    0.35
    POSITIVE LOGITS
     Webster
    0.40
     Directory
    0.34
     adds
    0.34
     προσ
    0.33
     Hung
    0.32
     excesses
    0.32
     가까
    0.32
     ↑
    0.32
     telescope
    0.32
    IBM
    0.32
    Act Density 0.001%

    No Known Activations