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

    Neuronpedia

    INDEX
    Explanations

    codes with numbers and dates

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     igre
    0.86
    襷
    0.85
     majeure
    0.83
    érique
    0.82
     DISTINCT
    0.82
    विध
    0.82
     고급
    0.81
    िलं
    0.80
    anyika
    0.80
    anova
    0.78
    POSITIVE LOGITS
    pportunities
    1.11
    fficial
    1.10
    pportun
    1.02
    xff
    0.95
    ct
    0.90
    ৫
    0.87
    xFF
    0.87
    ffic
    0.83
    xc
    0.83
    жа
    0.83
    Act Density 0.159%

    No Known Activations