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

    Neuronpedia

    INDEX
    Explanations

    measure

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    AMERA
    -0.06
    ゴ
    -0.06
     �
    -0.06
    ギ
    -0.06
    Barrier
    -0.06
    -0.06
    aan
    -0.06
    ств
    -0.06
     Voting
    -0.06
    кувати
    -0.06
    POSITIVE LOGITS
    supplier
    0.07
    擊
    0.07
     ｀
    0.07
     bargaining
    0.06
    'Re
    0.06
    _enable
    0.06
     Thoughts
    0.06
    때
    0.06
    TabControl
    0.06
     Occupational
    0.06
    Act Density 0.030%

    No Known Activations