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

    Neuronpedia

    INDEX
    Explanations

    learning RLHF

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     oč
    0.47
     olhos
    0.44
     playerCards
    0.41
    Hen
    0.39
     phú
    0.39
     شع
    0.38
     眼
    0.38
    🙉
    0.38
     ocul
    0.37
    esgue
    0.37
    POSITIVE LOGITS
    ಸ್ಸ
    0.39
    保障
    0.37
     asegura
    0.37
     seguirá
    0.37
     wasp
    0.37
     maybe
    0.36
     divert
    0.36
     ঘে
    0.36
    বর্তন
    0.36
     magari
    0.36
    Act Density 0.000%

    No Known Activations