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

    Neuronpedia

    INDEX
    Explanations

    text that expresses thoughts, reflections, or inquiries

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

    Comes after a period or question mark

    np_acts-logits-general · gemini-2.0-flash

    end of sentence contemplation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    THISDAY
    -0.71
    ungeon
    -0.68
     saites
    -0.66
    findpost
    -0.66
    brigens
    -0.64
     noqa
    -0.63
     duong
    -0.62
    YMMV
    -0.60
    horts
    -0.60
    niająca
    -0.60
    POSITIVE LOGITS
     Maybe
    0.62
     maybe
    0.62
     how
    0.62
     How
    0.61
     Surely
    0.60
    Surely
    0.60
     surely
    0.59
     Probably
    0.59
     Should
    0.58
    このまま
    0.57
    Act Density 0.125%

    No Known Activations