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

    Neuronpedia

    INDEX
    Explanations

    numerical scores and performance metrics

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

    scores and points

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ScopeManager
    -0.64
     AssemblyCompany
    -0.57
    XmlAccessorType
    -0.52
     JpaRepository
    -0.52
    +#+#
    -0.51
    AutoScaleMode
    -0.50
     lenker
    -0.49
    endregion
    -0.48
    بوابة
    -0.48
    KURZBESCHREIBUNG
    -0.47
    POSITIVE LOGITS
     scores
    0.67
     score
    0.60
    scores
    0.57
     puntuación
    0.56
     Scores
    0.54
     scored
    0.53
    Scores
    0.52
     ratings
    0.50
    score
    0.50
     scoring
    0.48
    Act Density 0.072%

    No Known Activations