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

    Neuronpedia

    INDEX
    Explanations

    operative

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _LOOKUP
    -0.07
     Lets
    -0.07
    Method
    -0.07
     carrier
    -0.07
     entering
    -0.07
    _No
    -0.06
     bend
    -0.06
    :@
    -0.06
    .Nullable
    -0.06
     Window
    -0.06
    POSITIVE LOGITS
     cowboy
    0.07
     росій
    0.06
    ج
    0.06
    forth
    0.06
    ppy
    0.06
    wie
    0.06
    gens
    0.06
    enské
    0.06
     сделать
    0.06
    رفته
    0.06
    Act Density 0.011%

    No Known Activations