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
     sugars
    -0.07
    ipmap
    -0.06
    KHR
    -0.06
     її
    -0.06
    onds
    -0.06
    FileStream
    -0.06
    我
    -0.06
     exploration
    -0.06
     walkers
    -0.06
     equivalent
    -0.06
    POSITIVE LOGITS
     unpl
    0.07
    (chalk
    0.07
    -inspired
    0.06
    Spirit
    0.06
    ByExample
    0.06
     Mattis
    0.06
     elegance
    0.06
    نش
    0.06
    _detalle
    0.06
     tess
    0.06
    Act Density 0.019%

    No Known Activations