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

    Neuronpedia

    INDEX
    Explanations

    statements and conclusions related to research findings and their implications

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

    followed by study results or findings

    np_acts-logits-general · gemini-2.0-flash

    our results/findings/data

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    exitRule
    -0.80
     ligiloj
    -0.76
     defaultstate
    -0.76
    IntoConstraints
    -0.75
    IsMutable
    -0.75
     viewDidLoad
    -0.73
    expandindo
    -0.69
     autorytatywna
    -0.69
    ⓧ
    -0.68
    RegressionTest
    -0.67
    POSITIVE LOGITS
     results
    3.00
    results
    2.49
     Results
    2.35
    Results
    2.32
     result
    2.25
     résultats
    2.19
     resultados
    2.13
     RESULTS
    2.07
     resultaten
    2.02
    result
    2.00
    Act Density 1.529%

    No Known Activations