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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     आध
    -0.06
     особист
    -0.06
     fungus
    -0.06
     Belfast
    -0.06
     urlencode
    -0.06
    ibold
    -0.06
     hob
    -0.06
    .Delete
    -0.06
     Radius
    -0.06
     münchen
    -0.06
    POSITIVE LOGITS
     المل
    0.08
     ребенка
    0.07
     thanked
    0.07
    เซ
    0.06
     squad
    0.06
    ником
    0.06
    стин
    0.06
    leneck
    0.06
    Bài
    0.06
     declar
    0.06
    Act Density 0.002%

    No Known Activations