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

    Neuronpedia

    INDEX
    Explanations

    programming constructs related to data structures and their manipulation

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

    Code, programming, or data-related terms

    np_acts-logits-general · gemini-2.0-flash

    programming language constructs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     one
    -0.49
    carboxylic
    -0.45
     válto
    -0.45
    </blockquote>
    -0.42
    ++
    -0.41
    imentel
    -0.41
     Ak
    -0.40
     terza
    -0.40
    ↵↵
    -0.40
    ője
    -0.40
    POSITIVE LOGITS
    RenderAtEndOf
    0.86
    IntoConstraints
    0.75
     myſelf
    0.73
    UnusedPrivate
    0.72
    <?
    0.70
    Personensuche
    0.69
    RegressionTest
    0.69
     itſelf
    0.68
    лтемелер
    0.68
    +#+#
    0.68
    Act Density 0.269%

    No Known Activations