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

    Neuronpedia

    INDEX
    Explanations

    lens

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    委员
    -0.08
     Legislative
    -0.07
    郓
    -0.07
    严禁
    -0.07
     TAX
    -0.07
    CONNECT
    -0.07
     LAST
    -0.07
     elemental
    -0.07
    好友
    -0.07
    녜
    -0.06
    POSITIVE LOGITS
    gerät
    0.07
    _paint
    0.07
    راحة
    0.07
     Kostenlos
    0.07
    افية
    0.07
    fills
    0.07
     overly
    0.07
     Führung
    0.07
    cccc
    0.07
     riêng
    0.07
    Act Density 0.016%

    No Known Activations