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

    Neuronpedia

    INDEX
    Explanations

    Foreign languages

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    新征程
    -0.07
     rewarded
    -0.07
     offsetX
    -0.07
    件事
    -0.07
    dda
    -0.07
     requestCode
    -0.07
    tensorflow
    -0.07
    @endforeach
    -0.06
    (Cs
    -0.06
    зыва
    -0.06
    POSITIVE LOGITS
    ítulo
    0.08
     Aub
    0.08
     Board
    0.07
    _goal
    0.07
     Mechanics
    0.07
     Stub
    0.07
    觉得
    0.07
    olucion
    0.07
    енная
    0.07
    undos
    0.07
    Act Density 0.009%

    No Known Activations