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

    Neuronpedia

    INDEX
    Explanations

    actions and classifications

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     الش
    0.47
    pixels
    0.46
    hrs
    0.45
    ADOW
    0.45
    այն
    0.45
    ニュ
    0.44
    جوم
    0.44
    늉
    0.44
    chtel
    0.44
    ۰۰
    0.43
    POSITIVE LOGITS
     ceremonial
    0.45
     Ih
    0.40
     ceremony
    0.39
     Rajapak
    0.39
     Kobayashi
    0.38
    mıştı
    0.38
     truy
    0.38
     deplorable
    0.38
     Mạnh
    0.38
     futhi
    0.38
    Act Density 0.001%

    No Known Activations