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

    Neuronpedia

    INDEX
    Explanations

    breakdown or explanation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     cosidd
    0.84
     tzv
    0.78
     tzw
    0.74
     maravilh
    0.73
    是我们
    0.67
     nossa
    0.64
     поэтому
    0.63
     sogenannte
    0.63
    私が
    0.63
     цих
    0.62
    POSITIVE LOGITS
     સમાચાર
    0.63
     കീഴ
    0.60
     전망
    0.60
    jTextField
    0.59
     തന്റെ
    0.59
     surprises
    0.59
    ື່ອ
    0.59
     తన
    0.58
    abhavam
    0.58
     خبر
    0.57
    Act Density 0.179%

    No Known Activations