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

    Neuronpedia

    INDEX
    Explanations

    simple, women, or job

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    emore
    0.43
     रियर
    0.42
    December
    0.41
    输
    0.39
    iembre
    0.39
     ambience
    0.38
    Hugh
    0.37
    })"
    0.37
     मोटरसाइकिल
    0.37
     зим
    0.37
    POSITIVE LOGITS
     AP
    0.43
     愛
    0.39
     Exposure
    0.39
    Spending
    0.39
     vertical
    0.38
     First
    0.37
    Exposure
    0.37
    ExposureTime
    0.37
     ##
    0.37
     ჩვენ
    0.37
    Act Density 0.000%

    No Known Activations