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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     mga
    -0.06
    	bool
    -0.06
    htm
    -0.06
    .remaining
    -0.06
    主任
    -0.06
    Recognizer
    -0.06
     domina
    -0.06
    tro
    -0.06
    Received
    -0.06
     Thankfully
    -0.06
    POSITIVE LOGITS
     오
    0.07
    ojení
    0.07
    CANCEL
    0.07
     polished
    0.06
     snapped
    0.06
    CNN
    0.06
     Discussion
    0.06
    _dyn
    0.06
     mx
    0.06
    ismu
    0.06
    Act Density 0.000%

    No Known Activations