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

    Neuronpedia

    INDEX
    Explanations

    elements related to programming syntax and operations

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

    Mathematical or code-related expressions

    np_acts-logits-general · gemini-2.0-flash

    input or test case identifiers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ValueStyle
    -0.65
     BoxDecoration
    -0.62
     AssemblyCulture
    -0.51
    adaptiveStyles
    -0.50
    ----</
    -0.50
    发表于
    -0.47
    клопе
    -0.46
    catori
    -0.45
     raggiunto
    -0.45
    RectangleBorder
    -0.44
    POSITIVE LOGITS
     input
    0.86
    testcase
    0.82
     Input
    0.81
    Input
    0.79
    input
    0.75
     INPUT
    0.69
     testCase
    0.68
     inputs
    0.68
    INPUT
    0.68
    输入
    0.67
    Act Density 0.277%

    No Known Activations