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

    Neuronpedia

    INDEX
    Explanations

    sections, parts, and references within a structured document, particularly in legal or technical contexts

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

    section headings or references

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    niſſe
    -0.77
    ſſung
    -0.75
    ſicht
    -0.73
    iſche
    -0.73
     للمعارف
    -0.70
    majánló
    -0.70
    ロウィン
    -0.69
    iſchen
    -0.69
    <unused21>
    -0.68
    <unused41>
    -0.68
    POSITIVE LOGITS
     tartalomajánló
    0.46
    はじめに
    0.39
    Espèce
    0.33
    0.33
    Према
    0.30
    ("")]
    0.26
    　
    0.26
    #
    0.25
    摘要
    0.25
    건
    0.25
    Act Density 0.006%

    No Known Activations