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

    Neuronpedia

    INDEX
    Explanations

    sigmoid function and cross-entropy

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    arr
    0.40
     daerah
    0.40
     Params
    0.40
    coords
    0.40
    del
    0.38
    stö
    0.38
    ชร์
    0.38
     cols
    0.38
    ّة
    0.37
     espace
    0.37
    POSITIVE LOGITS
    تج
    0.39
     빛
    0.39
     Irradiation
    0.39
     Bridgewater
    0.38
     adjudication
    0.38
    imiya
    0.37
     اعت
    0.37
     Advertisement
    0.36
     intimid
    0.36
     extré
    0.36
    Act Density 0.061%

    No Known Activations