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

    Neuronpedia

    INDEX
    Explanations

    Kits, kind, and kin

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ean
    0.40
     दृढ़
    0.37
     Huan
    0.36
     vir
    0.35
    ㄢ
    0.35
    न्यू
    0.34
    য়ো
    0.34
     Clans
    0.34
    ब
    0.34
    顓
    0.34
    POSITIVE LOGITS
     キ
    0.54
    㩴
    0.49
    kih
    0.48
     కి
    0.46
     unkind
    0.45
     Ки
    0.45
     ಕಿ
    0.44
    berly
    0.44
     kinet
    0.41
     kib
    0.41
    Act Density 0.011%

    No Known Activations