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

    Neuronpedia

    INDEX
    Explanations

    key-value assignment

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ंबकीय
    0.42
    NUCLEAR
    0.39
     splike
    0.38
    ંત્રણ
    0.36
    临床
    0.36
    鵰
    0.36
    ത്തും
    0.36
    ัพท์
    0.36
    手术
    0.35
    NuGet
    0.35
    POSITIVE LOGITS
    :
    0.69
    =
    0.62
     =
    0.50
    :,
    0.49
    ：
    0.45
    ='
    0.44
    ="
    0.43
    ,
    0.42
    ={
    0.41
     :
    0.40
    Act Density 0.098%

    No Known Activations