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

    Neuronpedia

    INDEX
    Explanations

    strength and power

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    묽
    0.46
    ücklich
    0.42
     Orbit
    0.41
     commuting
    0.41
     लिप
    0.41
     Oasis
    0.40
    ියාව
    0.40
    📝
    0.40
     wastewater
    0.40
    嗲
    0.40
    POSITIVE LOGITS
     strength
    1.21
    实力
    1.20
     powerful
    1.18
     firepower
    1.18
     formidable
    1.16
    strength
    1.12
     мощ
    1.10
     kekuatan
    1.10
    Powerful
    1.10
     शक्तिशाली
    1.09
    Act Density 0.044%

    No Known Activations