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

    Neuronpedia

    INDEX
    Explanations

    kotlin, java, scala imports

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     bolj
    0.26
    ouge
    0.25
     omkring
    0.24
     langsam
    0.24
     paraissent
    0.23
     hampir
    0.22
     bylo
    0.22
    the
    0.22
    0
    0.22
     alrededor
    0.22
    POSITIVE LOGITS
     ViewModel
    0.26
     UID
    0.25
    רי
    0.24
    하기
    0.24
     ዓይነ
    0.24
    希
    0.24
    銈
    0.24
     Ř
    0.23
     özellikleri
    0.23
    𒀭
    0.23
    Act Density 0.011%

    No Known Activations