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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating confusion or lack of understanding

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

    awareness and lack of awareness

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    verifyException
    -0.61
    kháu
    -0.52
    帖最后由
    -0.51
    Encyklopedia
    -0.45
    mbggenerated
    -0.45
     poire
    -0.44
     Grüsse
    -0.44
    Saluti
    -0.44
    inerja
    -0.43
    Than
    -0.42
    POSITIVE LOGITS
     unknown
    0.44
     unnoticed
    0.44
     oprot
    0.43
    يكب
    0.42
     forgot
    0.41
    glected
    0.40
     hidden
    0.38
     disambiguazione
    0.37
    жидан
    0.37
     unseen
    0.36
    Act Density 0.074%

    No Known Activations