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

    Neuronpedia

    INDEX
    Explanations

    string concatenation operations in code

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

    a plus sign followed by a variable

    np_acts-logits-general · gemini-2.0-flash

    programming code and variables

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ''
    -0.55
    dorff
    -0.53
    ("")){
    -0.51
    endpush
    -0.50
     &'
    -0.50
    iseite
    -0.47
    uis
    -0.46
     '';
    -0.46
    tión
    -0.46
     நட
    -0.45
    POSITIVE LOGITS
    IUrlHelper
    0.79
    withstanding
    0.79
     noqa
    0.73
    findpost
    0.73
    rzost
    0.68
    escaping
    0.67
    клопе
    0.67
    ⎯
    0.66
    ValueStyle
    0.66
    Gön
    0.65
    Act Density 0.032%

    No Known Activations