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

    Neuronpedia

    INDEX
    Explanations

    variations of the word "honor" and references to honors and awards

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

    honor or titles

    np_acts-logits-general · gemini-2.0-flash

    honorifics

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Искәрмәләр
    -0.58
    否
    -0.51
    Sucesor
    -0.49
    complexContent
    -0.49
    Enders
    -0.48
     TestBed
    -0.47
     wireType
    -0.46
     merce
    -0.46
    tadiene
    -0.45
    ieteur
    -0.45
    POSITIVE LOGITS
    HON
    0.83
     Mentions
    0.80
     sauvages
    0.78
     Mention
    0.77
     HON
    0.76
     dishon
    0.75
     محفوظة
    0.71
     荣耀
    0.70
     honneur
    0.68
     mention
    0.68
    Act Density 0.075%

    No Known Activations