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

    Neuronpedia

    INDEX
    Explanations

    terms associated with uncertainties and errors in measurements

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

    error and uncertainty calculation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Espèce
    -0.42
    ंदीखरीदारी
    -0.40
    :✨
    -0.37
     book
    -0.36
     Franch
    -0.35
    fahrzeuge
    -0.35
     ember
    -0.34
     books
    -0.34
    freopen
    -0.34
    吨
    -0.33
    POSITIVE LOGITS
    setViewportView
    0.59
     ddelweddau
    0.54
    MessageTagHelper
    0.52
    ThroughAttribute
    0.52
     '\\;'
    0.49
     veroor
    0.47
     verursacht
    0.47
    hirkan
    0.46
    MemoryWarning
    0.46
     wynika
    0.46
    Act Density 0.270%

    No Known Activations