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

    Neuronpedia

    INDEX
    Explanations

    expressions of opinion or appreciation in a text

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

    names and dates

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     raiſ
    -0.49
    parsedMessage
    -0.41
    ).]
    -0.41
    `).
    -0.40
    !).
    -0.40
    ."));
    -0.39
    ’).
    -0.39
    $​
    -0.38
    Personensuche
    -0.38
    ).
    -0.38
    POSITIVE LOGITS
    GraphicsUnit
    0.54
    цездатний
    0.53
    SourceChecksum
    0.51
     surla
    0.50
    OCCURRED
    0.50
     ویکی‌پدی
    0.49
    Gambas
    0.49
    iettes
    0.47
    bett
    0.46
     получится
    0.46
    Act Density 0.064%

    No Known Activations