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

    Neuronpedia

    INDEX
    Explanations

    Troubleshooting

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     voluntary
    -0.07
     panties
    -0.07
    ντ
    -0.07
     Erectile
    -0.06
     Yin
    -0.06
     dán
    -0.06
     Dillon
    -0.06
     denně
    -0.06
     програм
    -0.06
     Giấy
    -0.06
    POSITIVE LOGITS
     troubleshooting
    0.13
    leshoot
    0.10
    leshooting
    0.09
     troub
    0.08
    ub
    0.07
    baum
    0.07
    Ob
    0.06
     digging
    0.06
     Twig
    0.06
    izoph
    0.06
    Act Density 0.003%

    No Known Activations