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

    Neuronpedia

    INDEX
    Explanations

    bron

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ModelExpression
    -0.57
    IUrlHelper
    -0.56
     Toda
    -0.52
    GLP
    -0.51
     Fak
    -0.49
     Meilleures
    -0.48
     Aza
    -0.48
     lep
    -0.47
     Starship
    -0.47
     Habit
    -0.47
    POSITIVE LOGITS
     समीक्षाओं
    0.55
     utafiti
    0.53
     Schuster
    0.47
    enumi
    0.46
    الإنجليزية
    0.45
    发表于
    0.45
    chio
    0.45
    oghi
    0.45
    uncher
    0.45
     跳转至
    0.44
    Act Density 0.003%

    No Known Activations