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

    Neuronpedia

    INDEX
    Explanations

    news headlines and statistics

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ‒
    1.01
    ,—
    1.01
     Ā
    0.96
     cæ
    0.95
    ⁠
    0.92
    ʺ
    0.88
     Ō
    0.86
     Ś
    0.84
     Diarsipkan
    0.84
     Æ
    0.83
    POSITIVE LOGITS
     الصوره
    1.07
     Reagan
    0.95
     Soviets
    0.93
     UPI
    0.90
     नही
    0.89
    دايه
    0.88
     rumored
    0.87
     dijeron
    0.87
    ..
    0.86
     নির্মান
    0.85
    Act Density 0.010%

    No Known Activations