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

    Neuronpedia

    INDEX
    Explanations

    in

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     мил
    -0.07
    _DL
    -0.07
     эксплуата
    -0.07
    trer
    -0.07
    -Muslim
    -0.06
    kân
    -0.06
    361
    -0.06
     ayant
    -0.06
    _MP
    -0.06
    하우
    -0.06
    POSITIVE LOGITS
     savedInstanceState
    0.07
    (window
    0.06
    exc
    0.06
    award
    0.06
    ayscale
    0.06
     post
    0.06
    [l
    0.06
     fif
    0.06
    trand
    0.06
    healthy
    0.06
    Act Density 0.082%

    No Known Activations