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

    Neuronpedia

    INDEX
    Explanations

    app

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     anderen
    -0.07
    аном
    -0.07
    rase
    -0.06
    gence
    -0.06
    ане
    -0.06
    Sq
    -0.06
     autonomous
    -0.06
    ,{
    -0.06
    .ham
    -0.06
    flo
    -0.06
    POSITIVE LOGITS
    	endif
    0.06
     census
    0.06
    报名
    0.06
     خارج
    0.06
    ABL
    0.06
    Bus
    0.06
    健康
    0.06
     fal
    0.06
     bus
    0.06
     Benefits
    0.06
    Act Density 0.004%

    No Known Activations