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

    Neuronpedia

    INDEX
    Explanations

    managing python versions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     einsch
    0.48
    тери
    0.42
     сучас
    0.39
    োর্স
    0.38
     тера
    0.38
    nf
    0.38
     Боль
    0.38
     Karya
    0.38
     getData
    0.37
    getData
    0.37
    POSITIVE LOGITS
    全局
    0.45
     competing
    0.45
    Competing
    0.44
     global
    0.41
    デフォルト
    0.41
     globale
    0.41
    putable
    0.40
    Global
    0.40
    locations
    0.40
     globales
    0.40
    Act Density 0.010%

    No Known Activations