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

    Neuronpedia

    INDEX
    Explanations

    personal

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     cómo
    -0.07
    菟
    -0.07
    忳
    -0.07
    谷爱凌
    -0.07
    憷
    -0.07
    TÜ
    -0.07
    🤟
    -0.06
     Directions
    -0.06
    됩
    -0.06
    蒋介
    -0.06
    POSITIVE LOGITS
    .modal
    0.08
     exploded
    0.07
    广场
    0.07
     squadron
    0.07
    时间段
    0.07
    axis
    0.07
    .vaadin
    0.07
     ................................................................
    0.07
     von
    0.07
     terminal
    0.06
    Act Density 0.010%

    No Known Activations