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

    Neuronpedia

    INDEX
    Explanations

    2

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     образ
    -0.10
     сда
    -0.08
     очеред
    -0.08
     exemplary
    -0.08
    ировать
    -0.08
     richt
    -0.08
     расп
    -0.08
    identi
    -0.08
     fitte
    -0.08
    التالي
    -0.07
    POSITIVE LOGITS
     due
    0.09
     whereas
    0.09
    .alg
    0.08
    /E
    0.08
    .mac
    0.08
    ，也是
    0.08
     because
    0.08
     ואף
    0.07
    due
    0.07
     futhi
    0.07
    Act Density 0.023%

    No Known Activations