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

    Neuronpedia

    INDEX
    Explanations

    you

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    files
    -0.06
    lecture
    -0.06
     Snapshot
    -0.06
    ulong
    -0.06
    adopt
    -0.06
     masks
    -0.06
    _attempt
    -0.06
    люб
    -0.06
     :(
    -0.06
     mann
    -0.06
    POSITIVE LOGITS
     removeFromSuperview
    0.07
     نگ
    0.07
    __(*
    0.06
    .internet
    0.06
    상품
    0.06
    ประม
    0.06
    (range
    0.06
     Compar
    0.06
     обла
    0.06
     mies
    0.06
    Act Density 0.000%

    No Known Activations