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

    Neuronpedia

    INDEX
    Explanations

    based / induced / driven

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    an
    0.95
    a
    0.94
    i
    0.89
    er
    0.78
    average
    0.77
    ia
    0.76
    ا
    0.75
    seo
    0.75
    ers
    0.74
    eine
    0.73
    POSITIVE LOGITS
     만큼
    0.80
     potenz
    0.77
     ahi
    0.77
     للغاية
    0.76
     يس
    0.75
     proton
    0.75
    andez
    0.74
    рованной
    0.72
    ɴ
    0.72
    ис
    0.72
    Act Density 0.108%

    No Known Activations