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

    Neuronpedia

    INDEX
    Explanations

    Centers and Institutes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     filenames
    -0.09
    丁
    -0.08
    ffff
    -0.07
     yards
    -0.07
     individual's
    -0.07
    change
    -0.07
     Dunn
    -0.07
     gull
    -0.07
    uy
    -0.07
     negatives
    -0.07
    POSITIVE LOGITS
     dedicated
    0.12
     dédié
    0.11
     Dedicated
    0.11
     inaugurated
    0.11
     eingerichtet
    0.11
    Dedicated
    0.11
     gegründet
    0.10
     개최
    0.10
     opgericht
    0.10
     구축
    0.10
    Act Density 0.128%

    No Known Activations