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

    Neuronpedia

    INDEX
    Explanations

    a

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     wel
    -0.07
     умер
    -0.07
     setData
    -0.07
    Holiday
    -0.07
     khỏe
    -0.07
    .encoding
    -0.07
    登場
    -0.07
    (infile
    -0.07
    міністра
    -0.06
    .SizeF
    -0.06
    POSITIVE LOGITS
    Canadian
    0.06
     وان
    0.06
    �建
    0.06
    444
    0.06
    ιαν
    0.06
    AssignableFrom
    0.06
    514
    0.06
     bachelor
    0.06
     cogn
    0.06
    opo
    0.06
    Act Density 0.084%

    No Known Activations