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

    Neuronpedia

    INDEX
    Explanations

    Units of measurement

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    =n
    -0.07
    egin
    -0.07
    _ic
    -0.07
    (do
    -0.07
    ilon
    -0.07
     hott
    -0.06
     NPR
    -0.06
    ponde
    -0.06
     Hat
    -0.06
     FAILURE
    -0.06
    POSITIVE LOGITS
     principally
    0.07
     AVAILABLE
    0.06
     commonly
    0.06
    .description
    0.06
     absolutely
    0.06
     findViewById
    0.06
    _linked
    0.06
     los
    0.06
    Favorite
    0.05
    ensively
    0.05
    Act Density 0.027%

    No Known Activations