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

    Neuronpedia

    INDEX
    Explanations

    code, equations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     میدان
    -0.06
    함
    -0.06
    aktion
    -0.06
    ندق
    -0.06
    write
    -0.06
    부
    -0.06
    す
    -0.06
     verdiği
    -0.06
    icted
    -0.06
    .IS
    -0.06
    POSITIVE LOGITS
     Shooter
    0.07
     taste
    0.07
    ーニ
    0.06
     Virginia
    0.06
     Fire
    0.06
     searching
    0.06
     Menu
    0.06
    _UN
    0.06
     colonization
    0.06
    background
    0.06
    Act Density 0.000%

    No Known Activations