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

    Neuronpedia

    INDEX
    Explanations

    references to specific terms and terminology

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

    defining terminology

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Cyfeiriadau
    -0.42
    Demografía
    -0.35
     yemek
    -0.34
    lüğ
    -0.34
    simpan
    -0.33
     Social
    -0.33
    <i>
    -0.33
     social
    -0.32
     Liv
    -0.32
    Social
    -0.31
    POSITIVE LOGITS
     Resort
    0.98
    URLException
    0.63
     arşivlendi
    0.63
     Nomenclature
    0.61
     Terminology
    0.60
     terminology
    0.57
    Resort
    0.56
     adatt
    0.56
    BaseModel
    0.56
     nomenclature
    0.55
    Act Density 0.002%

    No Known Activations