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

    Neuronpedia

    INDEX
    Explanations

    expressions and reflections on personal thoughts and considerations

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

    thinking about

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    лтемелер
    -0.65
    :✨
    -0.61
    jsxFileName
    -0.58
    FunctionFlags
    -0.57
    endpush
    -0.56
    ❸
    -0.56
    VideoCapture
    -0.55
    ➟
    -0.55
    Tembelea
    -0.55
    endcsname
    -0.55
    POSITIVE LOGITS
    想过
    0.50
     thoughts
    0.40
     thinking
    0.40
     thought
    0.40
    Thoughts
    0.38
     THOUGHTS
    0.35
     pensando
    0.35
     pensé
    0.35
    thoughts
    0.35
    考えて
    0.34
    Act Density 0.030%

    No Known Activations