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

    Neuronpedia

    INDEX
    Explanations

    terms related to statistical measures of performance and diagnostic accuracy

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

    Statistical measures (sensitivity, specificity, etc.)

    np_acts-logits-general · gemini-2.0-flash

    sensitivity, specificity, predictive value

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Initializable
    -0.51
     turbul
    -0.49
     putra
    -0.45
     Turbulence
    -0.44
    flü
    -0.44
    Liên
    -0.42
     turbulence
    -0.42
     Turbul
    -0.42
    mt
    -0.41
    騰
    -0.41
    POSITIVE LOGITS
    참고
    0.74
     SwitchCompat
    0.72
     dichoto
    0.72
    PreferredItem
    0.71
     sumpay
    0.71
    SequentialGroup
    0.70
     scoring
    0.68
     false
    0.68
    confusion
    0.66
    CloseOperation
    0.64
    Act Density 0.835%

    No Known Activations