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

    Neuronpedia

    INDEX
    Explanations

    terms related to false positives and negatives in diagnostic testing

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

    false positive rate

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    shutil
    -0.52
     Administrativna
    -0.46
    Nosotros
    -0.43
     wish
    -0.43
    writerow
    -0.42
     Wikimedijinoj
    -0.41
     Ring
    -0.40
     habet
    -0.40
     sc
    -0.40
     ring
    -0.39
    POSITIVE LOGITS
    sizeCache
    0.73
    featureID
    0.62
    elemField
    0.59
    OGND
    0.54
    enderror
    0.52
    TokenNameDOT
    0.52
     facie
    0.49
    yntaxException
    0.47
    MessageWindow
    0.47
     jspb
    0.45
    Act Density 0.012%

    No Known Activations