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

    Neuronpedia

    INDEX
    Explanations

    numbers and code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    기
    0.87
    ó
    0.85
    म
    0.76
    ında
    0.73
    <0x92>
    0.70
    ாஹ
    0.69
    гра
    0.67
    이나
    0.65
    м
    0.65
    م
    0.65
    POSITIVE LOGITS
     Dodson
    0.92
     Lied
    0.90
     milhões
    0.78
     Flickr
    0.75
     USGS
    0.75
     deseo
    0.74
     বাদশা
    0.73
     Stimme
    0.73
     Eintrag
    0.73
    нке
    0.72
    Act Density 0.004%

    No Known Activations