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

    Neuronpedia

    INDEX
    Explanations

    terms related to conflict and resistance movements

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

    French words and abbreviations

    np_acts-logits-general · gemini-2.0-flash

    resistance and aggression

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     houſe
    -0.81
     myſelf
    -0.80
     betweenstory
    -0.77
     ſmall
    -0.77
     ſta
    -0.75
     faſt
    -0.75
     deſt
    -0.74
     pleaſure
    -0.73
     Efq
    -0.73
     uſe
    -0.73
    POSITIVE LOGITS
    TagHelper
    0.61
     é
    0.58
     ga
    0.56
     nor
    0.56
     ni
    0.55
    nga
    0.54
    valt
    0.53
     ne
    0.53
     neo
    0.53
     al
    0.52
    Act Density 0.096%

    No Known Activations