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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ��️
    -0.06
    Das
    -0.06
    ivariate
    -0.06
     Trit
    -0.06
     Assigned
    -0.06
     fing
    -0.06
    Deleting
    -0.06
    Symbols
    -0.06
    autos
    -0.06
              ↵
    -0.06
    POSITIVE LOGITS
    [word
    0.07
     ne
    0.07
     capacitor
    0.06
     comics
    0.06
    奴
    0.06
     crib
    0.06
    "][
    0.06
    (operation
    0.06
    Labels
    0.06
     disclosures
    0.06
    Act Density 0.027%

    No Known Activations