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

    Neuronpedia

    INDEX
    Explanations

    movie plot summaries

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     المادة
    -0.07
     velocity
    -0.07
     Winner
    -0.07
     第
    -0.07
    Physics
    -0.07
    ず
    -0.07
     Imagine
    -0.06
     праздник
    -0.06
     Article
    -0.06
     Purdue
    -0.06
    POSITIVE LOGITS
    "];
↵
    0.08
    ?v
    0.08
    治病
    0.07
    _MetadataUsageId
    0.07
    SessionFactory
    0.07
    Anal
    0.07
     słow
    0.07
    exampleModalLabel
    0.07
    裁员
    0.07
     unstoppable
    0.07
    Act Density 0.071%

    No Known Activations