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

    Neuronpedia

    INDEX
    Explanations

    wild

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    PHONE
    -0.08
    셋
    -0.07
     Fairfax
    -0.07
     ../../../
    -0.07
    춘
    -0.07
    戋
    -0.07
    -Con
    -0.07
     Schumer
    -0.07
    _Inter
    -0.07
     PROCESS
    -0.06
    POSITIVE LOGITS
     Wildcats
    0.08
     характер
    0.07
     specifying
    0.07
     реак
    0.07
     wildfire
    0.07
    posed
    0.07
    착
    0.07
    .btnDelete
    0.07
     terminating
    0.07
    =pd
    0.06
    Act Density 0.011%

    No Known Activations