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

    Neuronpedia

    INDEX
    Explanations

    limited, supports, paper, information, volume

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     forgo
    0.39
    Aula
    0.38
     panini
    0.38
    plasma
    0.38
     عز
    0.37
     تحصیل
    0.37
    culture
    0.37
    鎏
    0.37
     School
    0.37
    species
    0.36
    POSITIVE LOGITS
     মাথায়
    0.42
    _{*
    0.39
    년에
    0.39
    üp
    0.38
    
    0.38
    범
    0.38
    eture
    0.37
    iges
    0.36
    终端
    0.36
    喍
    0.36
    Act Density 0.000%

    No Known Activations