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

    Neuronpedia

    INDEX
    Explanations

    template literal syntax or variable interpolation in code

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

    Code that includes variable assignments and string interpolation

    np_acts-logits-general · gemini-2.0-flash

    string interpolation and code blocks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     faſt
    -0.49
    addGap
    -0.47
     Bubba
    -0.46
     getPassword
    -0.45
     '*')
    -0.44
     '.')
    -0.43
    pperware
    -0.42
    thma
    -0.42
     Савезне
    -0.42
     pageSize
    -0.42
    POSITIVE LOGITS
    (`${
    0.84
    ={`${
    0.76
    /#{
    0.75
    `${
    0.75
    WriteTagHelper
    0.75
    ($"{
    0.73
     `${
    0.69
     snippetHide
    0.60
    AddHtmlAttribute
    0.59
    devamını
    0.59
    Act Density 0.161%

    No Known Activations