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

    Neuronpedia

    INDEX
    Explanations

    description markers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     it
    0.54
     successo
    0.46
     being
    0.46
     එය
    0.44
    الش
    0.43
     fiind
    0.43
    の場合
    0.42
     processo
    0.42
     thereupon
    0.42
     secondly
    0.41
    POSITIVE LOGITS
     помогает
    0.54
     Indicates
    0.48
     غلط
    0.44
     толькі
    0.44
     поможет
    0.43
    umlah
    0.43
    ктери
    0.43
     Tells
    0.43
    可以让
    0.43
     experimentally
    0.42
    Act Density 0.113%

    No Known Activations