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

    Neuronpedia

    INDEX
    Explanations

    locations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    romosome
    -0.07
    ैठ
    -0.07
    dance
    -0.06
    ادی
    -0.06
    ูท
    -0.06
    ORIES
    -0.06
    ERY
    -0.06
     ↔
    -0.06
     مهند
    -0.06
    .Sprite
    -0.06
    POSITIVE LOGITS
    .${
    0.07
     prevented
    0.06
     notifies
    0.06
    \\
    0.06
     Hank
    0.06
     wy
    0.06
     uzak
    0.06
    GNU
    0.06
    (btn
    0.06
     wallpapers
    0.06
    Act Density 0.013%

    No Known Activations