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

    Neuronpedia

    INDEX
    Explanations

    codeproject.com/KB/

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    counter
    -0.75
    æl
    -0.71
    dée
    -0.71
    PackageManager
    -0.71
     lecker
    -0.71
    پی
    -0.71
    Nazionale
    -0.70
    کل
    -0.69
    疑
    -0.69
    ullen
    -0.68
    POSITIVE LOGITS
    到大
    0.82
    surgery
    0.70
    université
    0.70
    fotografía
    0.69
    llus
    0.68
     Bunt
    0.67
     پہ
    0.65
    mmc
    0.65
    Première
    0.64
    も同じ
    0.63
    Act Density 0.058%

    No Known Activations