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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     introdu
    -0.09
     introduction
    -0.09
     введ
    -0.08
     melhora
    -0.08
     introduced
    -0.07
    _answers
    -0.07
     Introduction
    -0.07
     melhor
    -0.07
     migliore
    -0.07
     introductions
    -0.07
    POSITIVE LOGITS
    اشت
    0.09
    ীব
    0.08
    سكرية
    0.08
    আই
    0.08
     адәм
    0.08
    Unnamed
    0.08
    ,omitempty
    0.08
    ।।
    0.08
     торм
    0.08
     unnamed
    0.08
    Act Density 0.077%

    No Known Activations