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

    Neuronpedia

    INDEX
    Explanations

    tables and their structural elements

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

    "Table" after an underscore

    np_acts-logits-general · gemini-2.0-flash

    tables

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Джерела
    -0.60
    Напомним
    -0.56
    Подробнее
    -0.52
    dataclass
    -0.52
    addPreferredGap
    -0.52
    SequentialGroup
    -0.51
    وقال
    -0.51
    المصادر
    -0.49
    Ecotoxicity
    -0.49
     gioielli
    -0.49
    POSITIVE LOGITS
     ddelweddau
    0.58
     незавершена
    0.56
    1
    0.54
    ->___
    0.52
     nahilalakip
    0.52
    file
    0.51
    件
    0.49
    ulemon
    0.49
     Fino
    0.49
    брь
    0.48
    Act Density 0.311%

    No Known Activations