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

    Neuronpedia

    INDEX
    Explanations

    suggested

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .DateField
    -0.06
     Miche
    -0.06
     дых
    -0.06
     stools
    -0.06
    '"
    -0.06
     editor
    -0.06
    Важ
    -0.05
     Влади
    -0.05
    vern
    -0.05
     Μη
    -0.05
    POSITIVE LOGITS
     jeux
    0.08
    .good
    0.07
    互
    0.07
    optimize
    0.07
    린
    0.07
     casing
    0.07
    ...");↵
    0.07
    ตา
    0.07
    --;↵
    0.07
    ичних
    0.07
    Act Density 0.000%

    No Known Activations