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

    Neuronpedia

    INDEX
    Explanations

    expressions of laughter or amusement

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

    starting with "ha" or "ra"

    np_acts-logits-general · gemini-2.0-flash

    haunted, raucous, hailed, haptic

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     للمعارف
    -0.97
     مشين
    -0.94
     שוליים
    -0.89
    XmlAccessorType
    -0.82
     himo
    -0.70
     Theſe
    -0.70
     '\\;'
    -0.67
    TintMode
    -0.64
    Scénario
    -0.63
     دریافت‌شده
    -0.63
    POSITIVE LOGITS
    Ra
    0.44
     αι
    0.44
     Ra
    0.43
    shire
    0.42
    きは
    0.41
    0.41
     po
    0.40
    sled
    0.40
     sho
    0.40
    ophy
    0.40
    Act Density 0.121%

    No Known Activations