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

    Neuronpedia

    INDEX
    Explanations

    occurrences of the word "it" and punctuation symbols used in programming contexts

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

    references to categories

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Administrativna
    -0.84
     Meksiku
    -0.69
     تضيفلها
    -0.66
     Italijani
    -0.62
    PYX
    -0.61
     protoimpl
    -0.60
    awaiter
    -0.60
    bouncycastle
    -0.58
    IsContent
    -0.58
     IFTT
    -0.57
    POSITIVE LOGITS
    لينكات
    0.43
    IContainer
    0.40
    eniendo
    0.32
     hautes
    0.28
    ñora
    0.27
     ]];
    0.27
     Nguyên
    0.26
     сим
    0.26
     procra
    0.25
    istisches
    0.25
    Act Density 0.001%

    No Known Activations