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

    Neuronpedia

    INDEX
    Explanations

    new products, services, and ideas

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ००
    2.23
    ১
    2.16
    ্টি
    2.12
    ниях
    2.07
    ﮩ
    2.04
    ‍♀️
    2.03
     remission
    2.03
    л
    2.02
    琶
    2.01
    认
    2.01
    POSITIVE LOGITS
    spapers
    3.38
     zealand
    3.03
    foundland
    2.84
    comers
    2.67
     सिरे
    2.67
    ви
    2.60
     york
    2.59
    found
    2.53
     minted
    2.50
     नवे
    2.44
    Act Density 0.201%

    No Known Activations