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

    Neuronpedia

    INDEX
    Explanations

    "Now"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     subsidiaries
    1.00
     beverages
    0.93
    te
    0.91
     grandchildren
    0.91
     biomarkers
    0.90
    er
    0.88
    ेड
    0.88
    ம்
    0.88
    ר
    0.87
     liabilities
    0.86
    POSITIVE LOGITS
     وبعد
    0.97
    好
    0.97
    不少
    0.96
     большое
    0.92
     этом
    0.91
    зи
    0.88
    ⓵
    0.88
    ３
    0.87
    жается
    0.86
     З
    0.85
    Act Density 0.002%

    No Known Activations