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

    Neuronpedia

    INDEX
    Explanations

    terms related to statistical measures and analysis

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

    Mathematical averages or means

    np_acts-logits-general · gemini-2.0-flash

    mean, average, statistics

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    烈
    -0.50
     입
    -0.45
     hinein
    -0.44
    hya
    -0.41
    сло
    -0.40
     ver
    -0.39
    ственная
    -0.39
    atini
    -0.38
    nola
    -0.38
     Incompatible
    -0.38
    POSITIVE LOGITS
     averages
    0.99
     average
    0.93
     averaging
    0.92
     averaged
    0.89
     Average
    0.87
    AVERAGE
    0.86
    average
    0.86
    Average
    0.86
     median
    0.85
     MonoBehaviour
    0.85
    Act Density 0.626%

    No Known Activations