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

    Neuronpedia

    INDEX
    Explanations

    other followed by category

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ट
    2.25
    ap
    2.06
    Quelle
    1.95
    TLE
    1.94
    TU
    1.92
    ל
    1.91
    TING
    1.90
    પણે
    1.88
    TS
    1.86
    сна
    1.86
    POSITIVE LOGITS
     Евро
    1.61
     biasa
    1.59
    纷纷
    1.56
    ként
    1.55
     sementara
    1.55
    मपुर
    1.50
    개월
    1.48
    ξε
    1.48
    ging
    1.44
     Bags
    1.42
    Act Density 0.150%

    No Known Activations