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
     kidneys
    -0.07
    alphabet
    -0.06
     vehicle
    -0.06
    department
    -0.06
    sto
    -0.06
     التن
    -0.06
     лют
    -0.06
     Rah
    -0.06
     zd
    -0.06
    لا
    -0.06
    POSITIVE LOGITS
    (TIM
    0.07
    .InnerException
    0.06
     допом
    0.06
     Tribal
    0.06
     interacts
    0.06
    ляется
    0.06
     hôm
    0.06
     ahora
    0.06
     employs
    0.06
    !)↵
    0.06
    Act Density 0.045%

    No Known Activations