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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -cylinder
    -0.08
     Thickness
    -0.08
    Thickness
    -0.08
     Thorough
    -0.08
     Cylinder
    -0.08
     Дет
    -0.08
     Danger
    -0.08
    aud
    -0.07
    Cylinder
    -0.07
     inoc
    -0.07
    POSITIVE LOGITS
     elegant
    0.09
    awaiter
    0.08
     syntax
    0.08
    新时代
    0.08
     readable
    0.08
    .syntax
    0.08
     elegance
    0.08
     lyrical
    0.08
     सिन
    0.08
     yona
    0.07
    Act Density 0.002%

    No Known Activations