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

    Neuronpedia

    INDEX
    Explanations

    discussions around democracy and its complexities

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

    Follows punctuation, especially commas and periods

    np_acts-logits-general · gemini-2.0-flash

    negation and imperfection

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     kasarigan
    -0.70
    ThroughAttribute
    -0.66
    cupa
    -0.65
    loyer
    -0.60
    adpleegd
    -0.60
     thiệu
    -0.59
    DataMember
    -0.54
    دانشنامهٔ
    -0.52
    contrib
    -0.51
    stackrel
    -0.51
    POSITIVE LOGITS
     imperfect
    0.76
     jamais
    0.73
     never
    0.67
     nécessairement
    0.65
    never
    0.64
     nooit
    0.63
     nigdy
    0.63
     NSCoder
    0.62
     nicio
    0.61
     imperfectly
    0.61
    Act Density 0.316%

    No Known Activations