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

    Neuronpedia

    INDEX
    Explanations

    numbers and percentages

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

    Numbers within parentheses

    np_acts-logits-general · gemini-2.0-flash

    numbers followed by numbers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Meksiku
    -0.70
     ninety
    -0.70
    ⁹
    -0.68
    tagHelperRunner
    -0.67
     unknownFields
    -0.67
     насељу
    -0.67
     nine
    -0.64
    enumi
    -0.63
    FormTagHelper
    -0.63
    aarrggbb
    -0.62
    POSITIVE LOGITS
    2
    0.49
     mariée
    0.48
    ủa
    0.47
     bronzo
    0.46
     morire
    0.44
     lég
    0.43
     salty
    0.42
    îmes
    0.42
    ︎
    0.42
    dataSource
    0.42
    Act Density 0.721%

    No Known Activations