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

    Neuronpedia

    INDEX
    Explanations

    Contributions and Rewards

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     picturesque
    -0.08
    遍
    -0.08
    Itr
    -0.08
    Iterable
    -0.08
    炮
    -0.08
     threaded
    -0.08
     trench
    -0.08
    Iterator
    -0.08
     marched
    -0.08
    ismen
    -0.08
    POSITIVE LOGITS
     kontrib
    0.12
     Contribution
    0.12
     पुरस्कार
    0.12
    奖励
    0.12
     बोनस
    0.12
     weighting
    0.12
    คะแนน
    0.11
    Contribution
    0.11
     bonus
    0.11
     бонус
    0.11
    Act Density 0.010%

    No Known Activations