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

    Neuronpedia

    INDEX
    Explanations

    file deletion

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    回答
    -0.06
    iga
    -0.06
     noci
    -0.06
    cores
    -0.06
    пион
    -0.06
    TES
    -0.06
    usty
    -0.06
     vacations
    -0.06
    702
    -0.06
    πό
    -0.06
    POSITIVE LOGITS
     ав
    0.07
    .maven
    0.07
     @$
    0.06
     vandalism
    0.06
    원의
    0.06
     Treasury
    0.06
     lä
    0.06
    .isEnabled
    0.06
     iterable
    0.06
     Кол
    0.06
    Act Density 0.007%

    No Known Activations