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

    Neuronpedia

    INDEX
    Explanations

    number

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Administrator
    0.66
    내가
    0.61
    Sugar
    0.60
    An
    0.58
    Ал
    0.58
    Agricult
    0.58
    A
    0.58
    Ah
    0.57
    私が
    0.57
    It
    0.56
    POSITIVE LOGITS
     of
    1.16
     delle
    0.85
     ofthe
    0.76
     của
    0.74
     della
    0.71
     των
    0.71
    ของการ
    0.69
    விடும்
    0.69
     ऑफ़
    0.69
     são
    0.68
    Act Density 0.000%

    No Known Activations