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

    Neuronpedia

    INDEX
    Explanations

    prepositions indicating direction or movement

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

    numerical ranges

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     arşivlendi
    -0.45
    attività
    -0.39
     selanjutnya
    -0.39
     vermelha
    -0.38
     aihe
    -0.38
     direito
    -0.37
     semuanya
    -0.37
     mijne
    -0.36
     Fassung
    -0.35
     zelve
    -0.35
    POSITIVE LOGITS
     oprot
    0.66
     numerus
    0.61
     CreateTagHelper
    0.60
    Rohy
    0.57
     nahilalakip
    0.57
    脚注の使い方
    0.56
    addPreferredGap
    0.55
    scrapy
    0.55
     noDo
    0.54
     Administrativna
    0.54
    Act Density 0.034%

    No Known Activations