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

    Neuronpedia

    INDEX
    Explanations

    how to use

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Restart
    0.48
    否则
    0.47
    containsKey
    0.45
     iniciado
    0.43
     ξεκ
    0.43
    Fal
    0.41
    Otherwise
    0.41
     iniziato
    0.41
     ക്യാ
    0.41
    Liên
    0.40
    POSITIVE LOGITS
     tropic
    0.41
     tutorial
    0.39
     followup
    0.39
     follow
    0.39
     fleet
    0.39
     example
    0.38
     sj
    0.38
     maximum
    0.38
     warp
    0.38
     Instructions
    0.37
    Act Density 0.001%

    No Known Activations