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

    Neuronpedia

    INDEX
    Explanations

    user-related identifiers and strings

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

    user attributes and actions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     people
    -0.49
     Menschen
    -0.44
     Russians
    -0.44
     Ukrainians
    -0.42
     humans
    -0.42
     individuals
    -0.39
     PEOPLE
    -0.39
     insanların
    -0.39
    นัก
    -0.39
     consumers
    -0.38
    POSITIVE LOGITS
     مرئيه
    0.54
     ProtoMessage
    0.52
     createState
    0.52
    verwijspagina
    0.52
     мәкал
    0.52
     jadx
    0.52
    bootstrapcdn
    0.51
    ligible
    0.51
     ThemeData
    0.51
    PyExc
    0.50
    Act Density 0.019%

    No Known Activations