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

    Neuronpedia

    INDEX
    Explanations

    formatted strings or syntax patterns used in programming languages

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

    Objective-C string formatting using `%@`

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    AddTagHelper
    -0.65
     ब्रेकडाउन
    -0.57
    новништво
    -0.57
     ujednoznacz
    -0.56
    DoubleQuotes
    -0.54
     estekak
    -0.54
     المعيارى
    -0.54
    UrlResolution
    -0.51
    PyExc
    -0.47
    jspx
    -0.47
    POSITIVE LOGITS
    :@"
    0.57
    ",@"
    0.54
    <<"
    0.52
    alala
    0.51
    kane
    0.50
    an
    0.48
    atem
    0.48
    isso
    0.47
    ['
    0.47
    fortunately
    0.46
    Act Density 0.008%

    No Known Activations