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

    Neuronpedia

    INDEX
    Explanations

    non-latin script characters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    কোনও
    0.44
     ....
    0.43
    ‘’
    0.42
     ...)
    0.40
     ‘’
    0.40
    ,’’
    0.40
    0.39
    0.39
     ’’
    0.38
    Thom
    0.38
    POSITIVE LOGITS
    Მ
    0.42
    Რ
    0.41
     siya
    0.41
    Გ
    0.39
    ってます
    0.39
     tiež
    0.38
    Ა
    0.38
    ная
    0.38
    了他的
    0.38
    🇧
    0.38
    Act Density 0.003%

    No Known Activations