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

    Neuronpedia

    INDEX
    Explanations

    dissection

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     المعيارى
    -0.61
    :✨
    -0.60
     تضيفلها
    -0.59
    الإنجليزية
    -0.57
    fetchone
    -0.57
    ñora
    -0.55
    новништво
    -0.55
     ImportError
    -0.54
    StructEnd
    -0.54
    adaptiveStyles
    -0.54
    POSITIVE LOGITS
     Site
    0.49
    UnitTesting
    0.49
     esté
    0.49
    staan
    0.47
     layui
    0.47
    insics
    0.46
     Gans
    0.46
    ais
    0.45
    ようです
    0.42
     vele
    0.42
    Act Density 0.011%

    No Known Activations