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

    Neuronpedia

    INDEX
    Explanations

    Numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (ext
    -0.08
     vede
    -0.07
     Supreme
    -0.07
     affection
    -0.07
     upgrades
    -0.07
     خدمت
    -0.07
     सिद्ध
    -0.07
     delir
    -0.07
     det
    -0.07
     episodio
    -0.07
    POSITIVE LOGITS
     dòng
    0.10
     vòng
    0.09
     folha
    0.09
     ಸಾಲ
    0.08
    コメント
    0.08
    橋
    0.08
     líneas
    0.08
     passen
    0.08
     comentários
    0.08
     लाइन
    0.08
    Act Density 0.006%

    No Known Activations