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

    Neuronpedia

    INDEX
    Explanations

    ambiguous traits, improved performance

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ए
    0.41
     omnibus
    0.41
    U
    0.40
    }\,
    0.38
     Đoàn
    0.38
     диску
    0.38
    bearing
    0.37
     unmittel
    0.37
    using
    0.37
    oulton
    0.37
    POSITIVE LOGITS
     অবস
    0.44
    并发
    0.39
    oki
    0.39
    pSensor
    0.39
     Qui
    0.38
     naked
    0.38
    并行
    0.38
    azam
    0.38
    naked
    0.38
     worship
    0.37
    Act Density 0.002%

    No Known Activations