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

    Neuronpedia

    INDEX
    Explanations

    Google AI models Gemini Gemma

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    t
    0.64
    as
    0.51
    ع
    0.50
    v
    0.49
    ت
    0.47
    a
    0.45
    ن
    0.45
    никова
    0.44
     Partizan
    0.44
     Kwiat
    0.44
    POSITIVE LOGITS
     doua
    0.48
    ﻒ
    0.48
    FORD
    0.48
    ardier
    0.47
     кноп
    0.46
     humming
    0.45
    svc
    0.44
    ethanol
    0.44
     класу
    0.44
     മനു
    0.43
    Act Density 0.104%

    No Known Activations