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

    Neuronpedia

    INDEX
    Explanations

    elements related to categories and classifications

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

    before suffixes like "s", "ing", "ed", or "un"

    np_acts-logits-general · gemini-2.0-flash

    typesetting, sideshow, rocks glass, meatspace

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    complexContent
    -0.65
     CURIAM
    -0.58
    schild
    -0.55
    GroupLayout
    -0.54
    LOTTE
    -0.54
    Candidate
    -0.53
    ISODE
    -0.52
    MessageTagHelper
    -0.52
    substack
    -0.52
    isSuccessful
    -0.51
    POSITIVE LOGITS
     تانيه
    0.72
    ſelves
    0.67
    >");
    0.65
    /></
    0.63
     itſelf
    0.60
     wireType
    0.59
     فريبيس
    0.57
     kaarangay
    0.57
    })();
    0.56
     مرئيه
    0.56
    Act Density 1.079%

    No Known Activations