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

    Neuronpedia

    INDEX
    Explanations

    pick

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     đ�
    -0.06
    cem
    -0.06
     courts
    -0.06
    SSION
    -0.06
     město
    -0.06
     tells
    -0.06
     dialect
    -0.06
    Amb
    -0.06
     немає
    -0.06
    	str
    -0.06
    POSITIVE LOGITS
     physique
    0.07
    ΙΚ
    0.06
     федераль
    0.06
    >:
    0.06
    ChildIndex
    0.06
     './../
    0.06
     />
    0.06
     recommendation
    0.06
    ImageData
    0.06
     Ivanka
    0.06
    Act Density 0.003%

    No Known Activations