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

    Neuronpedia

    INDEX
    Explanations

    as a python file

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     sugarcane
    0.69
    ใช้ง
    0.68
     пройдет
    0.67
     exclude
    0.67
     encouragement
    0.67
    getModel
    0.61
    ugeot
    0.60
    狈
    0.60
     spender
    0.60
    [.
    0.60
    POSITIVE LOGITS
    டிக
    0.71
    印
    0.70
    变量
    0.69
    ?”,
    0.69
     denominado
    0.66
     (\
    0.66
    undi
    0.65
    izados
    0.64
    ంటూ
    0.64
     Stati
    0.64
    Act Density 0.010%

    No Known Activations