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

    Neuronpedia

    INDEX
    Explanations

    instances of exclusivity or limited availability

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

    only

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    #
    -0.33
    //
    -0.32
    enumi
    -0.30
    -0.27
    ↵
    -0.27
    ‌ی
    -0.26
    UMEN
    -0.26
     [
    -0.25
    m
    -0.25
    <h4>
    -0.25
    POSITIVE LOGITS
    pecabe
    0.82
    ſicht
    0.80
    niſſe
    0.77
    ſſung
    0.75
    ésultats
    0.75
    <unused28>
    0.74
    出版年
    0.74
    <unused16>
    0.74
    <unused8>
    0.74
    [@BOS@]
    0.74
    Act Density 0.044%

    No Known Activations