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

    Neuronpedia

    INDEX
    Explanations

    hide/rename/add/remove/implement actions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    वाही
    0.36
    栄養
    0.36
    পান
    0.36
    त्वा
    0.36
     nourrir
    0.36
     florals
    0.36
    吃的
    0.35
    akkhati
    0.35
    ogany
    0.35
    CategoryImage
    0.34
    POSITIVE LOGITS
     IEEE
    0.40
     use
    0.38
     parameter
    0.38
     DMA
    0.37
     metadata
    0.37
     lossless
    0.37
     Unix
    0.36
     Copyright
    0.36
     CMOS
    0.36
    文字列
    0.36
    Act Density 0.001%

    No Known Activations