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

    Neuronpedia

    INDEX
    Explanations

    code structure delimiters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    BURY
    0.47
    йки
    0.45
    ंबकीय
    0.43
     ভাবে
    0.41
     hydrostatic
    0.40
    आईओएस
    0.40
    addSprite
    0.40
    টের
    0.40
    ūd
    0.40
    ക്കളുടെ
    0.40
    POSITIVE LOGITS
    ;
    0.54
     com
    0.45
    Autowired
    0.44
     _
    0.43
     @
    0.43
    ；
    0.41
    ,
    0.41
    .
    0.40
    (
    0.39
    /@
    0.37
    Act Density 0.001%

    No Known Activations