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

    Neuronpedia

    INDEX
    Explanations

    things you can control

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    distribution
    0.53
     ಹ
    0.52
     प्लेलिस्ट
    0.52
     პირ
    0.48
    აწ
    0.48
     lesen
    0.47
     STORIES
    0.47
     peeps
    0.47
    𝟏
    0.46
     Schritt
    0.46
    POSITIVE LOGITS
    ，
    0.48
    清单
    0.46
    )，
    0.46
    ните
    0.45
    趄
    0.45
    ్య
    0.43
     motionless
    0.42
    美
    0.42
     Chunk
    0.42
    лосо
    0.42
    Act Density 0.000%

    No Known Activations