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

    Neuronpedia

    INDEX
    Explanations

    JP

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     rabbit
    -0.07
     dof
    -0.07
    ús
    -0.07
    picture
    -0.07
     dinner
    -0.07
    Fixture
    -0.07
     horas
    -0.07
    对话
    -0.07
    .weapon
    -0.07
     Surgery
    -0.07
    POSITIVE LOGITS
    蹢
    0.08
    (\
    0.07
    .sent
    0.07
    .emplace
    0.07
    "How
    0.06
    arParams
    0.06
    Ꮋ
    0.06
    Lin
    0.06
    ">&
    0.06
     Ф
    0.06
    Act Density 0.004%

    No Known Activations