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

    Neuronpedia

    INDEX
    Explanations

    code structure and keywords

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Gly
    0.74
     organic
    0.72
     gly
    0.71
     poly
    0.69
     exotic
    0.68
     electronic
    0.67
     Cook
    0.67
     Hamilton
    0.66
     Vernon
    0.66
     salinity
    0.66
    POSITIVE LOGITS
     માં
    0.89
     Daher
    0.87
     När
    0.86
    Either
    0.84
     Toen
    0.84
     ながら
    0.84
    Else
    0.84
     或
    0.84
    प्रथम
    0.84
    őr
    0.84
    Act Density 0.435%

    No Known Activations