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

    Neuronpedia

    INDEX
    Explanations

    statistics and rates

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    רט
    -0.08
    /system
    -0.08
     сум
    -0.07
    ક
    -0.07
    ライト
    -0.07
    发生
    -0.07
    ⋄
    -0.07
    ☻
    -0.07
    郵
    -0.07
    ード
    -0.07
    POSITIVE LOGITS
     حت
    0.08
     Elo
    0.07
    Between
    0.07
    愆
    0.07
     createdAt
    0.07
    mAh
    0.07
     Marseille
    0.07
     likeness
    0.07
    _idxs
    0.07
    护身
    0.07
    Act Density 0.072%

    No Known Activations