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

    Neuronpedia

    INDEX
    Explanations

    kernel

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Dice
    -0.07
    utex
    -0.07
    하고
    -0.06
    your
    -0.06
    하지
    -0.06
     fon
    -0.06
    yll
    -0.06
     icons
    -0.06
    .organ
    -0.06
    dddd
    -0.06
    POSITIVE LOGITS
    .Model
    0.06
     MLA
    0.06
     чит
    0.06
     К
    0.06
    министра
    0.06
    蜘蛛
    0.06
    ='-
    0.06
    LERİ
    0.06
     Seller
    0.06
     thro
    0.06
    Act Density 0.006%

    No Known Activations