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

    Neuronpedia

    INDEX
    Explanations

    reinforcement learning

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    eti
    0.39
    ӳ
    0.38
    Val
    0.36
    ETO
    0.36
    Flo
    0.36
    VICIO
    0.36
    শোর
    0.35
     ऑक्सी
    0.35
    Roxy
    0.35
    Georges
    0.34
    POSITIVE LOGITS
    Фран
    0.40
    幢
    0.37
    䅛
    0.37
     dhan
    0.36
    _/
    0.35
    ጶ
    0.35
     divulg
    0.35
    ですから
    0.35
     designating
    0.35
    プリング
    0.34
    Act Density 0.007%

    No Known Activations