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

    Neuronpedia

    INDEX
    Explanations

    kernel, core, nucleus

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     বাতাসে
    0.47
    प्लीट
    0.44
     празд
    0.41
     मनाया
    0.40
    道歉
    0.39
    inka
    0.38
    ற்கான
    0.38
    പ്പെടുത്ത
    0.38
     terraz
    0.37
     फोर
    0.37
    POSITIVE LOGITS
     nucleus
    1.53
     kernel
    1.52
     core
    1.48
     núcleo
    1.48
     ядра
    1.45
     noyau
    1.43
    Kernel
    1.40
    内核
    1.39
     cores
    1.38
    nucleus
    1.38
    Act Density 0.031%

    No Known Activations