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

    Neuronpedia

    INDEX
    Explanations

    first tasks and unique characteristics

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    عرِّف
    0.45
    SignUp
    0.41
     गाँ
    0.40
     terc
    0.40
    ايبي
    0.39
     LXXX
    0.39
     Ettha
    0.38
     dépour
    0.38
     крепо
    0.38
    罅
    0.37
    POSITIVE LOGITS
    圆
    0.39
    &
    0.36
    twe
    0.36
    කාශ
    0.35
     spectra
    0.35
    ცხ
    0.35
     monochromatic
    0.34
    sides
    0.34
    lawful
    0.34
    Formula
    0.34
    Act Density 0.000%

    No Known Activations