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

    Neuronpedia

    INDEX
    Explanations

    overnight

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     wildlife
    -0.07
    San
    -0.06
    War
    -0.06
     меньше
    -0.06
     dette
    -0.06
    ізнес
    -0.06
     ken
    -0.06
    DataContext
    -0.06
     lokale
    -0.06
    mirror
    -0.06
    POSITIVE LOGITS
    _ISO
    0.07
    ｝
    0.07
    _nullable
    0.07
    ITS
    0.07
    Checkpoint
    0.07
    Κ
    0.07
    legate
    0.07
    _operand
    0.07
    .Addr
    0.06
    autoplay
    0.06
    Act Density 0.002%

    No Known Activations