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

    Neuronpedia

    INDEX
    Explanations

    instances of mathematical or logical symbols, particularly those related to operations or relations

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

    special characters and math notation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    tratamiento
    -0.31
    webElementXpaths
    -0.31
    发表于
    -0.30
     Cameron
    -0.29
    SuppressLint
    -0.29
    DataAnnotations
    -0.29
     Mulai
    -0.29
    SupportActionBar
    -0.28
     fenó
    -0.27
     esame
    -0.27
    POSITIVE LOGITS
     informée
    0.73
     kasarigan
    0.62
    protoimpl
    0.60
    windowFixed
    0.58
     SwitchCompat
    0.54
     виправивши
    0.53
    ंदीखरीदारी
    0.51
    0.51
     himſelf
    0.51
    伏
    0.50
    Act Density 0.025%

    No Known Activations