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

    Neuronpedia

    INDEX
    Explanations

    lists numbers and phrases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ორე
    1.26
     corretamente
    1.10
    涌
    1.05
     già
    1.05
    il
    1.02
    =>$
    1.02
    ্বক
    1.00
     Decreto
    1.00
     anteriormente
    0.99
    ство
    0.99
    POSITIVE LOGITS
    ت
    1.18
    sensor
    1.15
    т
    1.13
     pulpit
    1.09
    latency
    1.07
     capacitor
    1.05
     sequel
    1.05
    gripper
    1.03
    एँ
    1.02
     ample
    1.01
    Act Density 0.000%

    No Known Activations