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

    Neuronpedia

    INDEX
    Explanations

    initialization

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    plac
    0.41
    ল
    0.39
    স্ব
    0.37
    mce
    0.37
     зер
    0.36
    ángulos
    0.36
    ह्
    0.36
    炵
    0.36
    컥
    0.36
    ***************
    0.36
    POSITIVE LOGITS
     preparación
    0.43
     preparação
    0.41
     accomplish
    0.39
     prepares
    0.38
     preparar
    0.38
     processing
    0.37
     incurs
    0.37
    ರಿಕ
    0.37
     prepare
    0.37
     توهان
    0.36
    Act Density 0.002%

    No Known Activations