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

    Neuronpedia

    INDEX
    Explanations

    future steps and actions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     begr
    0.42
    reste
    0.39
     모두
    0.38
    령
    0.38
    သင့်
    0.37
     delinqu
    0.37
     bewusst
    0.37
     Ther
    0.37
     보면은
    0.37
     Kant
    0.36
    POSITIVE LOGITS
    irá
    0.43
     இனி
    0.41
    下一步
    0.40
    接下来
    0.40
     новую
    0.39
     новый
    0.39
     actual
    0.39
     nueva
    0.38
     henceforth
    0.38
     concurrently
    0.37
    Act Density 0.005%

    No Known Activations