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

    Neuronpedia

    INDEX
    Explanations

    religious texts interpretation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     توسیع
    0.40
     مسلح
    0.40
     नामित
    0.39
     Балт
    0.39
     রাহুল
    0.37
    apeut
    0.37
    мену
    0.37
     Tuti
    0.37
     لینا
    0.37
    𝘺
    0.37
    POSITIVE LOGITS
     små
    0.46
     ambient
    0.45
     small
    0.42
     kecil
    0.40
     negative
    0.39
     grievance
    0.38
    ambient
    0.38
    small
    0.37
    ~~~~
    0.37
     clo
    0.37
    Act Density 0.001%

    No Known Activations