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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     удал
    -0.08
    틴
    -0.06
    _qos
    -0.06
     dearly
    -0.06
     působ
    -0.06
    фік
    -0.06
     bardzo
    -0.06
     liebe
    -0.06
     дем
    -0.06
     beneficiary
    -0.06
    POSITIVE LOGITS
    υ
    0.07
     absolute
    0.06
    seconds
    0.06
    Yu
    0.06
     expectations
    0.06
     Important
    0.06
    _Close
    0.06
     Garmin
    0.06
     Item
    0.06
    ờ
    0.06
    Act Density 0.022%

    No Known Activations