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

    Neuronpedia

    INDEX
    Explanations

    concepts related to improvement, achievement, and progress

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

    proper nouns and foreign words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ongoing
    -0.37
     observers
    -0.36
     persistently
    -0.35
    toHave
    -0.35
     cog
    -0.34
     continued
    -0.34
     experienced
    -0.34
     виправивши
    -0.33
     emp
    -0.32
    체
    -0.32
    POSITIVE LOGITS
    Jereo
    0.73
    Jeografia
    0.65
     CURIAM
    0.65
    RTCK
    0.60
     ویکی‌پدی
    0.60
    Geplaatst
    0.57
     Comprometido
    0.56
     Wikimedijinoj
    0.56
     nôtre
    0.55
    Personendaten
    0.54
    Act Density 0.017%

    No Known Activations