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

    Neuronpedia

    INDEX
    Explanations

    references to safe and welcoming locations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    "place" or "places"

    np_acts-logits-general · gemini-2.0-flash

    place and description

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ViewFeatures
    -0.84
    OGND
    -0.79
    WithIOException
    -0.78
     protoimpl
    -0.74
     المعيارى
    -0.71
    routeProvider
    -0.69
     wireType
    -0.68
    aarrggbb
    -0.67
    FloatField
    -0.66
    الإنجليزية
    -0.65
    POSITIVE LOGITS
     where
    0.95
     places
    0.73
    Where
    0.72
     tempat
    0.70
    where
    0.67
     où
    0.65
     Where
    0.64
     place
    0.62
     WHERE
    0.62
    places
    0.59
    Act Density 0.100%

    No Known Activations