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

    Neuronpedia

    INDEX
    Explanations

    Code symbols

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     küçük
    -0.07
     solver
    -0.07
    coding
    -0.06
    USD
    -0.06
    odynamics
    -0.06
     subtitles
    -0.06
    akh
    -0.06
     Barcode
    -0.06
    尾
    -0.06
    iare
    -0.06
    POSITIVE LOGITS
    повід
    0.06
    「そう
    0.06
    -xl
    0.06
    (reordered
    0.06
     :/:
    0.06
    lâm
    0.06
    \F
    0.06
     �
    0.06
     sewing
    0.06
     челов
    0.06
    Act Density 0.024%

    No Known Activations