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

    Neuronpedia

    INDEX
    Explanations

    subprocess module in python

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    นี้
    0.47
    cipline
    0.45
    つの
    0.43
    の使用
    0.43
    Pack
    0.43
    しっかり
    0.41
     Moscou
    0.41
    ují
    0.40
    кау
    0.40
    Fuente
    0.40
    POSITIVE LOGITS
    ações
    0.49
     notably
    0.48
     preface
    0.41
     వా
    0.41
     immersed
    0.40
     glued
    0.40
     behaved
    0.38
     Eugen
    0.38
     geração
    0.38
     silvest
    0.38
    Act Density 0.001%

    No Known Activations