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

    Neuronpedia

    INDEX
    Explanations

    sections of text that contain high activation values, indicating key points or themes in documents

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

    Text after various punctuation or special characters

    np_acts-logits-general · gemini-2.0-flash

    code, mathematical, and legal phrases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ViewImports
    -0.56
    umab
    -0.48
     WaitForSeconds
    -0.48
    ∞
    -0.47
    عام
    -0.45
    ρώ
    -0.44
     requestCode
    -0.43
    MUN
    -0.43
    MLLoader
    -0.43
    wikimedia
    -0.42
    POSITIVE LOGITS
     Theſe
    0.70
     edelstahl
    0.68
     Monfieur
    0.66
    ыгана
    0.63
     mukana
    0.63
    KURZBESCHREIBUNG
    0.63
     Jefus
    0.62
     Efq
    0.61
    ⓧ
    0.60
    ніципалі
    0.60
    Act Density 0.097%

    No Known Activations