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

    Neuronpedia

    INDEX
    Explanations

    sequences or patterns related to numerical data representation or formatting

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

    separator lines

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ///</
    -0.40
    Kev
    -0.40
     getF
    -0.37
    FBI
    -0.33
    xF
    -0.32
    ethical
    -0.32
     onStart
    -0.32
     getPrice
    -0.32
    Rudy
    -0.31
     FBI
    -0.31
    POSITIVE LOGITS
     argint
    0.69
    ================
    0.66
     dezelve
    0.65
     derajat
    0.63
     mattino
    0.63
     moletom
    0.62
     administração
    0.61
     boneca
    0.61
    MethodManager
    0.61
    aarrggbb
    0.60
    Act Density 0.074%

    No Known Activations