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

    Neuronpedia

    INDEX
    Explanations

    CISSP, JIS, whiskies

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    HasFieldError
    0.46
    ftÂ
    0.40
    ลล์
    0.39
    titor
    0.39
    रिमेंट
    0.38
    enes
    0.38
    ingan
    0.38
     넘어
    0.38
    нский
    0.38
     것에
    0.38
    POSITIVE LOGITS
    consin
    0.53
    cuits
    0.44
    lamiento
    0.41
    пански
    0.40
    cosity
    0.40
    rael
    0.38
    とは
    0.38
    packet
    0.38
    десят
    0.38
    केक
    0.38
    Act Density 0.029%

    No Known Activations