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

    Neuronpedia

    INDEX
    Explanations

    y/and/or

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     и
    0.29
     καὶ
    0.28
     или
    0.27
     edhe
    0.27
    jenigen
    0.26
     ឬ
    0.25
     หรือ
    0.25
     historiques
    0.25
     PlayerSelector
    0.25
    уз
    0.25
    POSITIVE LOGITS
     sebagainya
    0.37
    /
    0.33
     whatnot
    0.32
    thew
    0.27
    www
    0.27
     में
    0.27
     the
    0.26
    ಗಳ
    0.26
    에서
    0.26
     tiež
    0.25
    Act Density 0.671%

    No Known Activations