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

    Neuronpedia

    INDEX
    Explanations

    creating content without explicit content

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ;
    0.51
     (
    0.49
    .
    0.49
    ,
    0.48
     :
    0.46
    r
    0.46
    -
    0.45
     ;
    0.44
    (
    0.44
    :
    0.43
    POSITIVE LOGITS
    स्पिटल
    0.46
     архів
    0.45
    ದುಕ
    0.44
     मुआव
    0.44
    ಚಿತ
    0.44
     добиться
    0.43
    ॅम्प
    0.43
     दामों
    0.43
    calup
    0.43
     ڈپاز
    0.42
    Act Density 0.001%

    No Known Activations