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

    Neuronpedia

    INDEX
    Explanations

    database passwords

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     SESSION
    -0.07
    .atom
    -0.07
    _ru
    -0.07
     initiator
    -0.06
     session
    -0.06
     наблю
    -0.06
    measure
    -0.06
     проблем
    -0.06
    ْر
    -0.06
    spots
    -0.06
    POSITIVE LOGITS
    اين
    0.07
    .MaxLength
    0.06
    ,{"
    0.06
    Incomplete
    0.06
    _Close
    0.06
     المست
    0.06
     vect
    0.06
     نبود
    0.06
    tele
    0.06
    _Settings
    0.06
    Act Density 0.231%

    No Known Activations