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

    Neuronpedia

    INDEX
    Explanations

    technology and technical terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     уні
    0.53
     полное
    0.49
     軍
    0.47
     बराबरी
    0.47
    applic
    0.46
     точке
    0.46
     процессе
    0.44
     матеріа
    0.44
     건설
    0.43
     метод
    0.43
    POSITIVE LOGITS
     B
    0.51
     Taliban
    0.50
     K
    0.50
     LED
    0.49
     M
    0.48
     P
    0.47
     V
    0.46
     PV
    0.44
     SO
    0.43
     Kas
    0.43
    Act Density 0.003%

    No Known Activations