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

    Neuronpedia

    INDEX
    Explanations

    adding to a set

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     alternative
    -0.08
    -0.07
     preval
    -0.07
     ne
    -0.07
     всех
    -0.07
    直接
    -0.07
     alternativa
    -0.07
     godi
    -0.07
    alternative
    -0.07
     Alternative
    -0.07
    POSITIVE LOGITS
     supplémentaire
    0.16
     toevoeg
    0.15
     추가
    0.15
     اضافه
    0.14
     additions
    0.14
     əlavə
    0.14
     ઉમ
    0.14
     supplémentaires
    0.14
     अतिरिक्त
    0.13
     tambahan
    0.13
    Act Density 0.065%
    No Known Activations