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

    Neuronpedia

    INDEX
    Explanations

    //

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     شدند
    -0.07
    )
    -0.07
    prod
    -0.07
    utex
    -0.07
     middleware
    -0.07
     IRQ
    -0.07
     fem
    -0.06
    Six
    -0.06
     Laws
    -0.06
    .diag
    -0.06
    POSITIVE LOGITS
     крас
    0.08
     hydrated
    0.07
     Cornwall
    0.07
    -grey
    0.06
     fazla
    0.06
    ytut
    0.06
     Claudia
    0.06
    ور
    0.06
    Density
    0.06
     olduğ
    0.06
    Act Density 0.008%

    No Known Activations