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

    Neuronpedia

    INDEX
    Explanations

    production

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    卫生
    -0.06
     irr
    -0.06
    shipping
    -0.06
     lax
    -0.06
     "&
    -0.06
    eating
    -0.06
    Fully
    -0.06
    .scale
    -0.06
     Subset
    -0.06
    _tau
    -0.06
    POSITIVE LOGITS
    věř
    0.07
     ราคา
    0.06
    izzer
    0.06
    �
    0.06
     отримання
    0.06
    ियल
    0.06
    b
    0.06
    acimiento
    0.06
     weld
    0.06
    .autoconfigure
    0.06
    Act Density 0.022%

    No Known Activations