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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and sentence endings

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

    End of sentences

    np_acts-logits-general · gemini-2.0-flash

    sentence ending punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Савезне
    -0.74
    Спољашње
    -0.64
     كومونز
    -0.63
    <bos>
    -0.62
     ویکی‌پدیا
    -0.62
     Мексичка
    -0.60
     joaat
    -0.59
    GraphicsUnit
    -0.58
     The
    -0.57
    openzeppelin
    -0.56
    POSITIVE LOGITS
    ↵↵
    1.38
    ↵
    0.94
    ↵↵↵
    0.94
    <eos>
    0.94
    ↵↵↵↵↵
    0.80
    ↵↵↵↵
    0.80
    </h3>
    0.73
    ↵↵↵↵↵↵↵
    0.72
    ↵↵↵↵↵↵
    0.71
    ↵↵↵↵↵↵↵↵↵↵↵
    0.70
    Act Density 0.570%

    No Known Activations