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

    Neuronpedia

    INDEX
    Explanations

    punctuational symbols and formatting elements commonly found in document structures

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

    diversity group labels

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Савезне
    -0.64
    richTextPanel
    -0.54
    تقاوى
    -0.51
    Viited
    -0.51
    хьтан
    -0.48
    yntaxException
    -0.48
    errHandler
    -0.48
     تضيفلها
    -0.47
    cinogenicity
    -0.47
    buttonBar
    -0.46
    POSITIVE LOGITS
     the
    0.71
     a
    0.52
    The
    0.44
    Third
    0.43
    zij
    0.43
     The
    0.42
    Second
    0.42
    indow
    0.40
    └──
    0.40
    fjspx
    0.40
    Act Density 0.042%

    No Known Activations