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

    Neuronpedia

    INDEX
    Explanations

    smoothness

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     A
    0.43
     "/
    0.42
     வலை
    0.40
     Tek
    0.39
     Air
    0.39
     Yuan
    0.39
     NZ
    0.39
     +
    0.39
     в
    0.38
     мно
    0.38
    POSITIVE LOGITS
    ikiem
    0.42
    urés
    0.41
    BRID
    0.41
    نیم
    0.40
     zeml
    0.40
    عی
    0.39
    সম্পাদকীয়
    0.39
     alkalies
    0.39
    杢
    0.38
    elje
    0.38
    Act Density 0.000%

    No Known Activations