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

    Neuronpedia

    INDEX
    Explanations

    asking for clarification or specifics

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    本発明
    0.80
    ff
    0.73
    彧
    0.72
    มนเชสเตอร์
    0.71
    婇
    0.68
    ાલુ
    0.65
    岱
    0.63
     автоматлары
    0.63
    爣
    0.61
    佺
    0.59
    POSITIVE LOGITS
    ?
    5.67
    ？
    5.39
    ??
    5.34
    ???
    5.20
    ?,
    5.18
     ?
    5.17
    ?!
    5.17
    ?:
    5.12
    ?????
    5.10
    ?(
    5.09
    Act Density 1.955%

    No Known Activations