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

    Neuronpedia

    INDEX
    Explanations

    answer

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    conomy
    -0.08
    [cnt
    -0.07
    abies
    -0.06
    enge
    -0.06
    achers
    -0.06
    ्यकत
    -0.06
    .Cos
    -0.06
     Lewis
    -0.06
    tığını
    -0.06
    luğ
    -0.06
    POSITIVE LOGITS
    луата
    0.07
     ді
    0.07
     exciting
    0.06
     Aleks
    0.06
     Alzheimer
    0.06
    ply
    0.06
    uellen
    0.06
     باع
    0.06
    ateral
    0.06
     sluggish
    0.06
    Act Density 0.006%

    No Known Activations