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

    Neuronpedia

    INDEX
    Explanations

    They

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _print
    -0.07
     Нав
    -0.07
    _rhs
    -0.06
    ğen
    -0.06
    games
    -0.06
    .setLocation
    -0.06
     free
    -0.06
     prejudice
    -0.06
    신청
    -0.06
    peror
    -0.06
    POSITIVE LOGITS
     Hardcore
    0.07
     ich
    0.07
    national
    0.07
    石
    0.06
     Aboriginal
    0.06
     consulted
    0.06
     DataManager
    0.06
    active
    0.06
     riff
    0.06
    KEY
    0.06
    Act Density 0.060%

    No Known Activations