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

    Neuronpedia

    INDEX
    Explanations

    terms related to population, geographic locations, and organizational categories

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

    places and categories

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     heavy
    -0.39
     
    -0.39
     run
    -0.37
    ble
    -0.36
    by
    -0.36
     flat
    -0.35
    ↵↵
    -0.35
    berday
    -0.35
    to
    -0.35
    2
    -0.35
    POSITIVE LOGITS
    Personendaten
    0.82
    httphttps
    0.82
     transfieras
    0.79
    GEBURTSDATUM
    0.75
    0.73
    出版年
    0.72
     незавершена
    0.71
    Portale
    0.69
    parsedMessage
    0.65
     ProtoMessage
    0.64
    Act Density 0.027%

    No Known Activations