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

    Neuronpedia

    INDEX
    Explanations

    formatting elements in technical or legal documents

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

    Non-English and unusual characters

    np_acts-logits-general · gemini-2.0-flash

    namespace, using

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     تضيفلها
    -0.75
    +#+#
    -0.62
    帖最后由
    -0.61
     تعدى
    -0.55
     intptr
    -0.54
     AssemblyCulture
    -0.52
    ္
    -0.51
     dren
    -0.49
     BoxDecoration
    -0.49
    moveToFirst
    -0.49
    POSITIVE LOGITS
     �
    1.13
    �
    0.91
     ��
    0.66
     '&#
    0.51
    ¿½
    0.51
    <?
    0.49
     '?'
    0.47
    fontWeight
    0.46
     posibil
    0.46
    ��
    0.46
    Act Density 0.333%

    No Known Activations