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

    Neuronpedia

    INDEX
    Explanations

    partitioning or division

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    rs
    0.65
    replay
    0.65
     teach
    0.64
     परिचालन
    0.64
     permissive
    0.63
    မ
    0.60
     rerun
    0.60
     ré
    0.60
     rêves
    0.60
    ﺮ
    0.60
    POSITIVE LOGITS
    divid
    0.70
    dP
    0.66
    cds
    0.64
     గ
    0.63
    دي
    0.63
    分区
    0.61
     gł
    0.61
    ദ്ധ
    0.61
    دة
    0.61
    partitions
    0.60
    Act Density 0.175%

    No Known Activations