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

    Neuronpedia

    INDEX
    Explanations

    =

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     রাষ্ট্র
    0.76
     government
    0.73
     रणनी
    0.71
    সরকারি
    0.69
    Col
    0.69
    government
    0.67
     strateg
    0.67
     michael
    0.67
     державної
    0.66
    symbol
    0.66
    POSITIVE LOGITS
    Steady
    0.70
     εμπ
    0.65
     제조업
    0.64
    啐
    0.63
     Steady
    0.63
    本作
    0.63
    เสมอ
    0.60
    來看
    0.59
    酘
    0.59
     FileMode
    0.59
    Act Density 0.003%

    No Known Activations