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

    Neuronpedia

    INDEX
    Explanations

    the glimpse beyond

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    蟲
    0.48
    クーポン
    0.47
    BackendAuth
    0.47
     nws
    0.47
    ncoder
    0.46
    ಬಹುದ
    0.46
     美術
    0.45
     Watan
    0.44
    ედერ
    0.44
     ASGI
    0.44
    POSITIVE LOGITS
     I
    0.56
    ice
    0.49
    K
    0.45
     i
    0.44
     ello
    0.43
    Kol
    0.42
    artige
    0.42
    endo
    0.42
     ice
    0.42
    El
    0.41
    Act Density 0.002%

    No Known Activations