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

    Neuronpedia

    INDEX
    Explanations

    debate

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     daun
    -0.08
     storing
    -0.08
     troph
    -0.08
    对象
    -0.08
     Yarn
    -0.07
     korting
    -0.07
    存
    -0.07
    .ids
    -0.07
    (objects
    -0.07
    .Tasks
    -0.07
    POSITIVE LOGITS
     hearings
    0.09
    比赛
    0.09
     प्रतियोग
    0.08
     журналист
    0.08
     proceedings
    0.08
     वक्त
    0.08
    NBC
    0.08
     speeches
    0.08
     moderator
    0.08
    Moderator
    0.08
    Act Density 0.010%

    No Known Activations