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

    Neuronpedia

    INDEX
    Explanations

    daily

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     clf
    -0.07
     Fan
    -0.06
    clf
    -0.06
     gotta
    -0.06
    mund
    -0.06
     vertices
    -0.06
     skinny
    -0.06
    şt
    -0.06
     honorary
    -0.06
    Pro
    -0.06
    POSITIVE LOGITS
    erness
    0.07
     предвар
    0.06
    ".
    0.06
    /win
    0.06
    .annotations
    0.06
    ?↵
    0.06
    .Invoke
    0.06
     UITableViewDataSource
    0.06
    icing
    0.06
    (",")↵
    0.06
    Act Density 0.000%

    No Known Activations