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

    Neuronpedia

    INDEX
    Explanations

    terms related to quality and health outcomes

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

    preceding evaluations (good, poor, excellent)

    np_acts-logits-general · gemini-2.0-flash

    quality judgments

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ($__
    -0.58
    jsonwebtoken
    -0.57
    DockStyle
    -0.56
    invokeLater
    -0.56
    unculus
    -0.53
    istert
    -0.52
    abus
    -0.51
    artifactId
    -0.50
    ladung
    -0.50
    cipe
    -0.49
    POSITIVE LOGITS
     quality
    1.06
    quality
    0.95
     schlechter
    0.90
     snippetHide
    0.86
     Quality
    0.85
     Good
    0.84
    Quality
    0.83
     QUALITY
    0.83
     good
    0.82
     buruk
    0.82
    Act Density 0.308%

    No Known Activations