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

    Neuronpedia

    INDEX
    Explanations

    references to statistical or mathematical data structures and operations

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

    special characters and code brackets

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Personendaten
    -0.62
    msgTypes
    -0.62
    Spoljašnje
    -0.61
    帖最后由
    -0.58
    ंदीखरीदारी
    -0.58
    цездатний
    -0.55
    Chham
    -0.53
    contentLoaded
    -0.52
    SourceChecksum
    -0.52
     Мексичка
    -0.51
    POSITIVE LOGITS
    phosa
    0.43
    墟
    0.31
     alone
    0.31
    つく
    0.31
     Apart
    0.31
    áver
    0.31
     Dig
    0.30
     Duck
    0.29
    แน
    0.29
     opro
    0.29
    Act Density 0.552%

    No Known Activations