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

    Neuronpedia

    INDEX
    Explanations

    instances of specific numerical or positional information

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

    numbers and punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    windowFixed
    -0.82
    تقاوى
    -0.77
    queryInterface
    -0.66
    Personensuche
    -0.66
     AppCompatTheme
    -0.66
     oprot
    -0.64
     MenuView
    -0.62
    GEBURTSDATUM
    -0.62
    EndGlobalSection
    -0.59
    ItemBackground
    -0.55
    POSITIVE LOGITS
     cuillère
    0.41
     Hidup
    0.40
     titulada
    0.39
     bruja
    0.39
     muñecas
    0.39
     menemukan
    0.39
     kepad
    0.39
     Füßen
    0.38
    aksikan
    0.38
    해서
    0.37
    Act Density 0.028%

    No Known Activations