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

    Neuronpedia

    INDEX
    Explanations

    understanding

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    CHA
    -0.07
     accessed
    -0.07
     Must
    -0.07
     refugees
    -0.07
     Chic
    -0.07
     slim
    -0.06
     Alma
    -0.06
     citizenship
    -0.06
    し�
    -0.06
     dzieci
    -0.06
    POSITIVE LOGITS
    _ROUND
    0.07
     článku
    0.07
    {EIF
    0.06
     utilise
    0.06
     assms
    0.06
     فيه
    0.06
     leather
    0.06
     피
    0.06
    ยง
    0.06
     setback
    0.06
    Act Density 0.055%

    No Known Activations