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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and structural elements typical in written documents, particularly in legal or formal contexts

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

    Solving equations or comparing numbers

    np_acts-logits-general · gemini-2.0-flash

    solving equations and comparisons

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    mek
    -0.52
    <em>
    -0.49
    ській
    -0.49
    <i>
    -0.48
     
    -0.46
    amp
    -0.46
     “
    -0.46
    <sup>
    -0.45
    <strong>
    -0.45
     inf
    -0.44
    POSITIVE LOGITS
     متعلقه
    1.04
     kasarigan
    0.98
    ContentAsync
    0.91
    IntoConstraints
    0.88
    AndEndTag
    0.88
    +#+#
    0.87
     تانيه
    0.86
     الحره
    0.83
     المعيارى
    0.83
     AssemblyTitle
    0.81
    Act Density 0.302%

    No Known Activations