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

    Neuronpedia

    INDEX
    Explanations

    class definition or inheritance

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     når
    0.23
     diamètre
    0.23
    ganggu
    0.22
    urètre
    0.22
    ะนั้น
    0.22
    شانی
    0.21
    ateg
    0.21
     Omphalodes
    0.21
     maksimum
    0.21
     nejsou
    0.21
    POSITIVE LOGITS
     a
    0.30
     the
    0.28
     J
    0.28
     B
    0.27
     C
    0.26
     F
    0.25
     P
    0.25
     M
    0.24
     Business
    0.24
     in
    0.24
    Act Density 0.207%

    No Known Activations