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

    Neuronpedia

    INDEX
    Explanations

    terminology and concepts related to programming and software development

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

    mathematical or typesetting markup

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     surla
    -0.84
     Geſch
    -0.84
    TagMode
    -0.81
     beſte
    -0.78
     مرئيه
    -0.77
    AnchorTagHelper
    -0.77
     ſei
    -0.77
    queryInterface
    -0.77
     ſind
    -0.76
     فريبيس
    -0.76
    POSITIVE LOGITS
    .
    0.39
    ;
    0.37
    <tbody>
    0.36
    :
    0.36
     
    0.35
    <eos>
    0.35
    ,
    0.34
    ason
    0.34
     :
    0.33
    ：
    0.33
    Act Density 0.000%

    No Known Activations