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

    Neuronpedia

    INDEX
    Explanations

    numbers followed by Days

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ी
    2.92
    greSQL
    2.66
    ];//
    2.52
    杷
    2.50
    bait
    2.45
    }\|
    2.45
    ೃಷ್ಣ
    2.38
    separable
    2.35
     سمت
    2.35
    ord
    2.33
    POSITIVE LOGITS
    ляется
    3.00
    ل
    2.77
     dahulu
    2.74
    arom
    2.55
    ير
    2.50
    𝘁
    2.46
    Lors
    2.43
    al
    2.43
    ።
    2.41
     fro
    2.40
    Act Density 0.102%

    No Known Activations