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

    Neuronpedia

    INDEX
    Explanations

    app/USER profile content

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ফা
    0.68
     kel
    0.68
     LSTM
    0.67
     Ты
    0.66
     amélior
    0.65
    elen
    0.64
     Panda
    0.64
     जमी
    0.64
     clot
    0.64
     PACK
    0.64
    POSITIVE LOGITS
    content
    1.54
     content
    1.37
    widget
    1.30
    Content
    1.21
     Content
    1.05
    os
    1.03
     conteúdo
    1.00
    内容
    0.99
    app
    0.98
     widget
    0.97
    Act Density 0.142%

    No Known Activations