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

    Neuronpedia

    INDEX
    Explanations

    references to levels of analysis or organization in various contexts

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

    scope and scale

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    typeorm
    -0.49
    testify
    -0.39
    正解
    -0.39
     aloft
    -0.39
    ếp
    -0.39
    endregion
    -0.38
    ofy
    -0.38
    ofür
    -0.37
    draw
    -0.37
    arom
    -0.37
    POSITIVE LOGITS
     المعيارى
    0.60
     صوتيه
    0.57
    audiovisuel
    0.56
    OGND
    0.52
     meubles
    0.48
     вікісторінку
    0.44
    OrEmpty
    0.43
     الحره
    0.43
     <=",
    0.43
     lenker
    0.42
    Act Density 0.159%

    No Known Activations