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

    Neuronpedia

    INDEX
    Explanations

    what * or What *

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Lifestyle
    0.52
    Machine
    0.52
    ד
    0.52
    Simple
    0.50
    From
    0.49
    大量
    0.49
    Rough
    0.48
    Consumption
    0.48
    Listener
    0.47
    全部
    0.47
    POSITIVE LOGITS
     namam
    0.50
     ut
    0.48
     ویب
    0.48
     permiss
    0.48
     reconstit
    0.47
     essa
    0.47
     participar
    0.47
     reste
    0.46
    atthena
    0.46
    یسر
    0.45
    Act Density 0.000%

    No Known Activations