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

    Neuronpedia

    INDEX
    Explanations

    terms expressing varying degrees of abundance or presence

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

    adverbs of degree in multiple languages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    PreferredItem
    -0.75
     surla
    -0.61
    Хьажоргаш
    -0.57
     EconPapers
    -0.57
    mapStateToProps
    -0.57
    ksesta
    -0.56
     mapStateToProps
    -0.56
    󠁢
    -0.55
    싶
    -0.54
    lcccc
    -0.53
    POSITIVE LOGITS
     מש
    0.68
    倒
    0.52
     muito
    0.52
     המש
    0.51
    Muito
    0.48
    aspectRatio
    0.48
     ό
    0.47
     مش
    0.47
     במש
    0.46
    muito
    0.46
    Act Density 0.003%

    No Known Activations