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

    Neuronpedia

    INDEX
    Explanations

    here,,

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    дят
    0.59
     همچ
    0.57
     ferv
    0.56
    дзе
    0.54
     closed
    0.54
    最後まで
    0.54
     zad
    0.53
    зонта
    0.53
    边
    0.52
    胺
    0.52
    POSITIVE LOGITS
    MENT
    0.67
    glie
    0.65
    পট
    0.64
    ‣
    0.64
    ⋅
    0.64
    OT
    0.60
    ческий
    0.60
    pective
    0.60
    𝑥
    0.60
     onPressed
    0.59
    Act Density 0.007%

    No Known Activations