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

    Neuronpedia

    INDEX
    Explanations

    Revealing hidden information

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     landslide
    -0.07
     Memories
    -0.07
    Mon
    -0.06
     Myst
    -0.06
     RNA
    -0.06
    enger
    -0.06
     byte
    -0.06
    "Not
    -0.06
     Mutual
    -0.06
    roducing
    -0.06
    POSITIVE LOGITS
    _purchase
    0.07
     환경
    0.06
     graphical
    0.06
    sizlik
    0.06
     artifacts
    0.06
     FName
    0.06
    である
    0.06
     받
    0.06
     trom
    0.06
     ris
    0.06
    Act Density 0.069%

    No Known Activations