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

    Neuronpedia

    INDEX
    Explanations

    GPU training

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Anh
    -0.07
     iletişim
    -0.07
     Sail
    -0.07
    wear
    -0.07
    cen
    -0.07
    анов
    -0.06
     Greene
    -0.06
    iyah
    -0.06
    .warn
    -0.06
    тап
    -0.06
    POSITIVE LOGITS
    .route
    0.06
    σα
    0.06
     navigationController
    0.06
    Carthy
    0.06
    <S
    0.06
     jj
    0.06
     getSupportActionBar
    0.05
    окрема
    0.05
     essays
    0.05
    	transform
    0.05
    Act Density 0.070%

    No Known Activations