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

    Neuronpedia

    INDEX
    Explanations

    Months

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Patton
    -0.06
    ским
    -0.06
     Tem
    -0.06
     своїх
    -0.06
     optimized
    -0.06
    _ACC
    -0.06
    Numbers
    -0.06
    工程
    -0.06
     Colum
    -0.06
     coercion
    -0.06
    POSITIVE LOGITS
    ])
↵
↵
    0.07
     результате
    0.06
    >D
    0.06
     факт
    0.06
     injust
    0.06
    ár
    0.06
     Орг
    0.06
     gestures
    0.06
     可
    0.06
    riteln
    0.06
    Act Density 0.011%

    No Known Activations