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

    Neuronpedia

    INDEX
    Explanations

    numerical comparisons and values related to averages and deviations

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

    measurement relative to a threshold

    np_acts-logits-general · gemini-2.0-flash

    greater than or less than

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     AssemblyCulture
    -0.54
    ArgsConstructor
    -0.47
     faſt
    -0.43
    reportWebVitals
    -0.42
    OGND
    -0.42
     ſtand
    -0.42
    vertx
    -0.37
    routeProvider
    -0.37
     ſte
    -0.36
    isEnd
    -0.35
    POSITIVE LOGITS
     than
    0.71
    than
    0.60
     ब्रेकडाउन
    0.60
     THAN
    0.60
    principalColumn
    0.59
    THAN
    0.56
     än
    0.55
     niż
    0.55
    Than
    0.52
     Than
    0.50
    Act Density 0.582%

    No Known Activations