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

    Neuronpedia

    INDEX
    Explanations

    our

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    istä
    1.09
    លោក
    1.04
    }],
    1.02
    កំព
    0.99
    或許
    0.99
    oit
    0.96
    }))
    0.96
     suas
    0.95
     âg
    0.94
    ud
    0.93
    POSITIVE LOGITS
    га
    1.28
    िक
    1.27
    িক
    1.23
    ية
    1.23
    า
    1.14
    ్
    1.13
    ных
    1.12
    ки
    1.11
    ار
    1.09
    ні
    1.09
    Act Density 0.229%

    No Known Activations