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

    Neuronpedia

    INDEX
    Explanations

    firstly, first, first steps

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ición
    0.48
     habitats
    0.46
     iCloud
    0.45
    сти
    0.44
    捙
    0.42
     coni
    0.42
    itani
    0.42
     alligator
    0.42
     Crew
    0.42
     retains
    0.42
    POSITIVE LOGITS
    まず
    0.49
     اولا
    0.46
    :(
    0.46
     firstly
    0.46
    一方面
    0.43
    Therefore
    0.43
    GameObject
    0.42
    你看
    0.41
    Gli
    0.41
    Firstly
    0.41
    Act Density 0.010%

    No Known Activations