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

    Neuronpedia

    INDEX
    Explanations

    exclamatory expressions and emotional responses

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

    a mistake or correction

    np_acts-logits-general · gemini-2.0-flash

    end of statement

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    tvguidetime
    -0.67
    <bos>
    -0.63
     }}$}
    -0.60
    <%@
    -0.53
    */;
    -0.53
     which
    -0.51
     المعيارى
    -0.51
    ']))
    -0.50
    ])));
    -0.50
     untere
    -0.49
    POSITIVE LOGITS
    rungsseite
    0.71
    richTextPanel
    0.66
    ArgumentParser
    0.61
     Paglinawan
    0.60
     kasarigan
    0.59
    SharedDtor
    0.56
     amigos
    0.55
    ikiki
    0.55
     amigo
    0.55
    ViewFeatures
    0.53
    Act Density 0.295%

    No Known Activations