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

    Neuronpedia

    INDEX
    Explanations

    working with entities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     wraz
    0.56
     junto
    0.46
    自分で
    0.44
    compared
    0.43
    遇见
    0.43
     עם
    0.40
     కనిప
    0.38
    ряду
    0.38
     Zusammenhang
    0.37
     compared
    0.37
    POSITIVE LOGITS
     membentuk
    0.61
     forming
    0.58
     посредством
    0.56
     formando
    0.55
     seamlessly
    0.51
     mutually
    0.50
     sharing
    0.50
     via
    0.48
     regarding
    0.46
     форми
    0.46
    Act Density 0.032%

    No Known Activations