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

    Neuronpedia

    INDEX
    Explanations

    tokens with a predominance of whitespace or empty spaces

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

    Followed by numbers

    np_acts-logits-general · gemini-2.0-flash

    various languages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    OGND
    -0.69
    Diweddarwch
    -0.65
     المعيارى
    -0.60
     nakalista
    -0.60
    Jeografia
    -0.56
     незавершена
    -0.54
    #+#
    -0.54
    IndentedString
    -0.51
    脚注の使い方
    -0.50
    ⟬
    -0.49
    POSITIVE LOGITS
    libatkan
    0.50
    lihatan
    0.48
     nyky
    0.48
    ตน
    0.47
    олові
    0.47
     leão
    0.46
     amortecedor
    0.45
     ää
    0.45
     moverse
    0.45
    ijão
    0.44
    Act Density 0.413%

    No Known Activations