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

    Neuronpedia

    INDEX
    Explanations

    throws

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     relación
    -0.08
     themselves
    -0.07
     Thompson
    -0.07
     ngoài
    -0.07
     Kol
    -0.07
     ngồi
    -0.07
    帮你
    -0.07
     Jurassic
    -0.07
     nargs
    -0.06
     tentang
    -0.06
    POSITIVE LOGITS
    pictureBox
    0.07
    gabe
    0.07
    농
    0.07
    ]').
    0.07
    詩
    0.07
    -build
    0.07
    鼷
    0.07
     Fest
    0.07
    ReadStream
    0.07
    سرط
    0.07
    Act Density 0.006%

    No Known Activations