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

    Neuronpedia

    INDEX
    Explanations

    special characters and formatting symbols

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

    Ignores conversational text; finds code or math formulas

    np_acts-logits-general · gemini-2.0-flash

    special characters and code snippets

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Chwiliwch
    -0.65
     kaarangay
    -0.60
    iſen
    -0.56
     &___
    -0.52
     AssemblyTitle
    -0.50
     وتسجيلات
    -0.49
    Enllaces
    -0.49
    AccessorTable
    -0.48
    Билгалдахарш
    -0.47
     tartalomajánló
    -0.47
    POSITIVE LOGITS
    httphttps
    0.55
    addContainerGap
    0.48
    endregion
    0.44
    endphp
    0.44
    enderror
    0.40
     jScrollPane
    0.39
    WillAppear
    0.39
    endpush
    0.39
    sworth
    0.38
    endgroup
    0.38
    Act Density 1.130%

    No Known Activations