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

    Neuronpedia

    INDEX
    Explanations

    code snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     нар
    -0.06
    итися
    -0.06
    /card
    -0.06
    .activities
    -0.06
    enario
    -0.06
     reveals
    -0.06
     Archbishop
    -0.06
    (arg
    -0.06
     Religious
    -0.06
     operators
    -0.05
    POSITIVE LOGITS
     MS
    0.07
     Deadline
    0.07
     Chick
    0.07
     testim
    0.07
    .Flush
    0.07
    如果
    0.07
     zlib
    0.07
     已
    0.07
     rozší
    0.06
    .validate
    0.06
    Act Density 0.087%

    No Known Activations