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

    Neuronpedia

    INDEX
    Explanations

    references to programming concepts and operations

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

    questions regarding implementation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     consultas
    -0.43
    findpost
    -0.43
    principalTable
    -0.42
    Huile
    -0.40
     Chwiliwch
    -0.39
    チール
    -0.39
    Portály
    -0.39
     immigrants
    -0.39
    setString
    -0.39
     الرياضيه
    -0.39
    POSITIVE LOGITS
    
    0.54
     Conti
    0.44
    tagext
    0.42
     تعدى
    0.41
    Примітки
    0.39
    مند
    0.38
     Employ
    0.38
    tonode
    0.37
    ✭✭
    0.36
     İ
    0.36
    Act Density 0.133%

    No Known Activations