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

    Neuronpedia

    INDEX
    Explanations

    possess or provide with emphasis

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     dicho
    0.45
     weiter
    0.38
     Weitere
    0.36
     fieldContext
    0.36
    fahrung
    0.36
    ኪያ
    0.36
    YL
    0.35
    Tarjeta
    0.35
    有人
    0.35
    FIED
    0.35
    POSITIVE LOGITS
     unparalleled
    0.58
     unprecedented
    0.57
     unrival
    0.50
     extraordinarily
    0.49
     самые
    0.47
     truly
    0.46
     incredibly
    0.45
     unusually
    0.45
     настолько
    0.44
     remarkably
    0.43
    Act Density 0.008%

    No Known Activations