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

    Neuronpedia

    INDEX
    Explanations

    include

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Xxx
    -0.08
    ,q
    -0.07
    ,but
    -0.06
     отд
    -0.06
    跑
    -0.06
     amber
    -0.06
    (concat
    -0.06
     towns
    -0.06
     uống
    -0.06
    .thread
    -0.06
    POSITIVE LOGITS
    ump
    0.07
    βολή
    0.07
    )[:
    0.07
    INCLUDE
    0.06
    aunch
    0.06
    ERİ
    0.06
     expelled
    0.06
    avra
    0.06
    ozřejmě
    0.06
    abei
    0.06
    Act Density 0.004%

    No Known Activations