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

    Neuronpedia

    INDEX
    Explanations

    attributes related to notable individuals and their accomplishments

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

    after common words or punctuation

    np_acts-logits-general · gemini-2.0-flash

    English professional drama and society

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    /***/
    -0.56
     Signalez
    -0.54
     vidéo
    -0.54
    หวัด
    -0.52
    OGND
    -0.52
    principalTable
    -0.51
     Empowerment
    -0.51
    HasForeignKey
    -0.51
    EReference
    -0.50
    #![
    -0.48
    POSITIVE LOGITS
    存于互联网档案馆
    0.64
     lyric
    0.61
     liter
    0.58
     volup
    0.57
     الرياضيه
    0.57
     ornament
    0.54
     belles
    0.53
     oratory
    0.53
     rhetor
    0.53
     makeStyles
    0.53
    Act Density 0.285%

    No Known Activations