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

    Neuronpedia

    INDEX
    Explanations

    in

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Suppliers
    -0.07
     키
    -0.07
    шка
    -0.06
     caz
    -0.06
    blocking
    -0.06
     flavorful
    -0.06
     janvier
    -0.06
     MATRIX
    -0.06
     Spirit
    -0.06
     utilizes
    -0.06
    POSITIVE LOGITS
    -header
    0.07
    μ
    0.07
    Breadcrumb
    0.07
    /thumb
    0.06
    Partial
    0.06
     setImage
    0.06
    ferences
    0.06
     تحلیل
    0.06
     Δ
    0.06
    \v
    0.06
    Act Density 0.028%

    No Known Activations