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

    Neuronpedia

    INDEX
    Explanations

    math

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    cakes
    -0.07
    cede
    -0.06
     кра
    -0.06
     muse
    -0.06
     IE
    -0.06
     Crop
    -0.05
    utility
    -0.05
     Milk
    -0.05
     Doll
    -0.05
     cigar
    -0.05
    POSITIVE LOGITS
    arton
    0.08
    .maven
    0.08
     영향을
    0.07
     Wordpress
    0.07
    WordPress
    0.07
     fm
    0.07
     모든
    0.07
    .isEnabled
    0.07
     يجب
    0.07
     були
    0.07
    Act Density 0.006%

    No Known Activations