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

    Neuronpedia

    INDEX
    Explanations

    stack traces

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     possessions
    -0.06
     её
    -0.06
    _TREE
    -0.06
     수
    -0.06
     wm
    -0.06
    307
    -0.06
     IllegalAccessException
    -0.06
    �
    -0.06
    _war
    -0.06
    _recipe
    -0.05
    POSITIVE LOGITS
    劉
    0.07
    =response
    0.07
    aryawan
    0.07
    accumulator
    0.06
     ничего
    0.06
    ाँ
    0.06
     被
    0.06
    IVEN
    0.06
    糖
    0.06
    .branch
    0.06
    Act Density 0.003%

    No Known Activations