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

    Neuronpedia

    INDEX
    Explanations

    architecture

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Dv
    -0.09
     bowel
    -0.08
    DQ
    -0.08
     cooker
    -0.08
     preschool
    -0.08
     Pob
    -0.07
     QModel
    -0.07
    ilir
    -0.07
     rémun
    -0.07
     elementary
    -0.07
    POSITIVE LOGITS
    师
    0.09
    .Vertex
    0.08
     dams
    0.08
    �
    0.08
     photography
    0.08
    摄影
    0.08
     inclined
    0.08
    Postal
    0.07
    Photography
    0.07
     pleasing
    0.07
    Act Density 0.008%

    No Known Activations