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

    Neuronpedia

    INDEX
    Explanations

    the start of a new section or paragraph in the document

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

    physical states and awareness

    np_acts-logits-general · gemini-2.0-flash

    waking up beside

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     personal
    -0.53
    cloudfront
    -0.49
    igshid
    -0.48
    tructive
    -0.48
    论
    -0.47
     متعلقه
    -0.47
     serve
    -0.47
    Xna
    -0.46
     drive
    -0.46
    mium
    -0.45
    POSITIVE LOGITS
     groaning
    0.68
     waking
    0.67
     dazed
    0.63
     woken
    0.62
     doulou
    0.61
     dying
    0.60
     awoke
    0.59
     regaining
    0.58
    consciousness
    0.58
     consciousness
    0.57
    Act Density 0.206%

    No Known Activations