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

    Neuronpedia

    INDEX
    Explanations

    Graph Theory

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     boost
    0.37
     Zhao
    0.37
     Syn
    0.36
     roundup
    0.36
    Go
    0.36
     removal
    0.36
     Synchron
    0.35
     Sun
    0.35
     shadow
    0.35
     Folk
    0.35
    POSITIVE LOGITS
    ĕ
    0.38
    उन
    0.34
    зили
    0.34
     مرد
    0.34
    тое
    0.33
    리스마
    0.33
     दिली
    0.32
    ERAL
    0.31
    вари
    0.31
    லே
    0.31
    Act Density 0.001%

    No Known Activations