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

    Neuronpedia

    INDEX
    Explanations

    quantitative comparisons and measurements

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

    fraction, levels, pre-

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     فريبيس
    -0.50
     <>",
    -0.46
     كومونز
    -0.46
    LookAnd
    -0.44
     resourceCulture
    -0.44
     szól
    -0.37
    MessageTagHelper
    -0.36
    énario
    -0.36
    yarnpkg
    -0.35
     geç
    -0.34
    POSITIVE LOGITS
     intptr
    0.49
    msgTypes
    0.42
    mergeFrom
    0.41
     pathname
    0.41
    nasium
    0.40
    &__
    0.40
    ntgen
    0.40
     fraction
    0.40
    bollah
    0.40
    tawesome
    0.39
    Act Density 0.197%

    No Known Activations