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

    Neuronpedia

    INDEX
    Explanations

    examine information sources

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ovana
    0.85
    relatively
    0.79
    ravariant
    0.79
    bersome
    0.76
    asiswa
    0.76
    unknown
    0.75
    cimiento
    0.75
    icultural
    0.73
    teurs
    0.71
     incomparable
    0.71
    POSITIVE LOGITS
     documentation
    1.10
     logs
    1.09
     archives
    1.02
     textbooks
    0.96
     documents
    0.92
     recent
    0.92
     spreadsheets
    0.91
     labels
    0.90
     records
    0.90
     screenshots
    0.89
    Act Density 0.097%

    No Known Activations