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

    Neuronpedia

    INDEX
    Explanations

    Wikipedia encyclopedia

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     گیری
    1.47
     prestigious
    1.18
     recursion
    1.18
     Mesmo
    1.16
    هور
    1.16
    ্যান্ড
    1.11
     zal
    1.10
    ᖓ
    1.08
    ‖</
    1.08
    enment
    1.07
    POSITIVE LOGITS
    it
    1.32
     refrain
    1.26
    ска
    1.23
    itize
    1.21
    Waterfall
    1.19
    রাও
    1.14
    ક્રિયા
    1.13
    ле
    1.12
     checkbox
    1.08
    พา
    1.08
    Act Density 0.001%

    No Known Activations