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

    Neuronpedia

    INDEX
    Explanations

    draw

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     activated
    -0.07
    ンの
    -0.06
    cd
    -0.06
     Nigeria
    -0.06
    Hy
    -0.06
     Tri
    -0.06
     обов
    -0.06
    的に
    -0.06
    kovou
    -0.06
    utive
    -0.06
    POSITIVE LOGITS
     empire
    0.07
    lets
    0.07
     scaleFactor
    0.06
    (operation
    0.06
     incorporate
    0.06
     ulaş
    0.06
    upert
    0.06
    .bottomAnchor
    0.06
    +"</
    0.06
     allegation
    0.06
    Act Density 0.004%

    No Known Activations