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

    Neuronpedia

    INDEX
    Explanations

    (Intent

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -ver
    -0.07
    oring
    -0.07
    orna
    -0.07
     aggress
    -0.06
     ще
    -0.06
    átu
    -0.06
     measurable
    -0.06
    stand
    -0.06
     BER
    -0.06
     yielding
    -0.06
    POSITIVE LOGITS
    (Intent
    0.11
    .jsdelivr
    0.09
    cepts
    0.07
     pizzas
    0.06
    rels
    0.06
    .bias
    0.06
     Vik
    0.06
     disturb
    0.06
    政策
    0.06
    ��
    0.06
    Act Density 0.000%

    No Known Activations