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

    Neuronpedia

    INDEX
    Explanations

    web documentation and code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    х
    0.90
    рых
    0.89
    CES
    0.88
    лос
    0.86
    ל
    0.85
    со
    0.85
    ir
    0.84
    鎌
    0.82
    NES
    0.80
    стов
    0.80
    POSITIVE LOGITS
     společnost
    1.11
    เมื่อ
    1.02
    टरनेट
    0.94
     oamenii
    0.91
     iniziare
    0.89
     eerder
    0.88
     relazioni
    0.87
    เริ่ม
    0.86
     substantially
    0.84
     kezd
    0.84
    Act Density 0.001%

    No Known Activations