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

    Neuronpedia

    INDEX
    Explanations

    references to critical and reflective thinking processes

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

    thinking and thinkers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ビデオ
    -0.38
     Oates
    -0.37
    getNum
    -0.35
    urlopen
    -0.35
     few
    -0.35
    <bos>
    -0.35
     Kade
    -0.35
    yelitis
    -0.34
     Paragon
    -0.34
     tuyệt
    -0.33
    POSITIVE LOGITS
     thinker
    0.95
    thinking
    0.94
     Thinking
    0.90
     thinking
    0.90
     thinkers
    0.90
    Thinking
    0.87
     THINK
    0.85
     Think
    0.82
    think
    0.81
    Think
    0.79
    Act Density 0.012%

    No Known Activations