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

    Neuronpedia

    INDEX
    Explanations

    blank or whitespace characters

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

    numbers and digits

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ویکی‌پدیای
    -0.58
     Photocase
    -0.54
    IContainer
    -0.53
    GEBURTS
    -0.50
    <bos>
    -0.48
    Personendaten
    -0.47
     виправивши
    -0.47
    аза
    -0.45
    +#+#
    -0.45
    Controllo
    -0.45
    POSITIVE LOGITS
     )}$
    0.41
    \{\\
    0.41
     ”
    0.39
     thiệu
    0.36
     )
    0.36
     Kulit
    0.36
    Herzliche
    0.36
     cruel
    0.36
     formal
    0.35
    ":"",
    0.35
    Act Density 0.017%

    No Known Activations