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

    Neuronpedia

    INDEX
    Explanations

    Data tables

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     од
    -0.07
    Mat
    -0.07
    FullName
    -0.07
     film
    -0.07
    嗯
    -0.07
     movie
    -0.06
     vad
    -0.06
    -0.06
     Buk
    -0.06
    DataContext
    -0.06
    POSITIVE LOGITS
     dispar
    0.06
    sm
    0.06
    shop
    0.06
    gear
    0.06
    Angle
    0.06
     Dedicated
    0.06
     flashes
    0.06
     Dealers
    0.06
    .BOLD
    0.06
    ALIGN
    0.06
    Act Density 0.092%

    No Known Activations