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

    Neuronpedia

    INDEX
    Explanations

    meaning of words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     giriş
    0.50
     puriso
    0.48
     ორი
    0.47
     тести
    0.46
    ோ
    0.46
     cres
    0.46
     سرکاری
    0.45
    poems
    0.45
     prepara
    0.44
     kri
    0.44
    POSITIVE LOGITS
     Что
    0.43
     Seine
    0.42
    溯
    0.42
    意味
    0.41
     Zijn
    0.41
     Weight
    0.41
     Meaning
    0.41
     MRS
    0.41
     అందు
    0.40
    任何人
    0.40
    Act Density 0.002%

    No Known Activations