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

    Neuronpedia

    INDEX
    Explanations

    power, control, and trauma

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ially
    0.97
    ly
    0.92
    ভাবে
    0.90
     dhan
    0.89
     frequented
    0.87
    astica
    0.86
    ahme
    0.85
    mente
    0.84
    astic
    0.83
    ewhat
    0.82
    POSITIVE LOGITS
     Genres
    1.08
     morphisms
    1.08
     वहीं
    1.03
     conduit
    1.02
     τὸ
    0.98
     войны
    0.96
     innocence
    0.96
    Genres
    0.95
    ចាំ
    0.95
     icin
    0.94
    Act Density 0.066%

    No Known Activations