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

    Neuronpedia

    INDEX
    Explanations

    numbers, math, code, dates

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ගත
    1.09
    ᴹ
    1.05
     adhesions
    1.04
     disparate
    1.04
     adhesives
    1.01
     Adhesive
    1.00
     Maven
    0.99
    𝚜
    0.99
     propres
    0.99
     blueprints
    0.98
    POSITIVE LOGITS
    ه
    1.35
    د
    1.12
    eighth
    1.11
    هُ
    1.04
    u
    1.01
    uously
    1.00
    borderRadius
    0.90
    ندق
    0.89
    |
    0.89
    ＝
    0.88
    Act Density 0.197%

    No Known Activations