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

    Neuronpedia

    INDEX
    Explanations

    proper nouns in a professional context

    oai_token-act-pair · gemini-2.0-flash

    organizations

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ViewImports
    -0.80
     المعيارى
    -0.73
     lumineuse
    -0.72
     myſelf
    -0.71
    SharedCtor
    -0.71
    ViewFeatures
    -0.70
     heureuse
    -0.68
     Roskov
    -0.67
     zelve
    -0.66
    setVerticalGroup
    -0.66
    POSITIVE LOGITS
     ${
    0.56
     staff
    0.55
    <sup>
    0.55
     g
    0.54
    etor
    0.53
     he
    0.52
     the
    0.51
     “
    0.51
    ol
    0.50
     gl
    0.50
    Act Density 11.907%

    No Known Activations