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

    Neuronpedia

    INDEX
    Explanations

    still + adjective/adverb

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ної
    1.66
    gewicht
    1.59
    みました
    1.55
    იდან
    1.41
    ujesz
    1.38
     Grilled
    1.38
    ﻱ
    1.38
    ﻯ
    1.37
    িকে
    1.30
    не
    1.30
    POSITIVE LOGITS
    m
    1.76
    ל
    1.61
    م
    1.52
    ד
    1.45
    म
    1.40
    لی
    1.26
     וע
    1.25
     plenty
    1.23
    з
    1.23
    К
    1.19
    Act Density 0.192%

    No Known Activations