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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Edition
    -0.07
     Working
    -0.07
     Keller
    -0.07
     Mac
    -0.07
     Owen
    -0.07
    _rgba
    -0.06
    itioner
    -0.06
     editions
    -0.06
    ic
    -0.06
     LAW
    -0.06
    POSITIVE LOGITS
     slides
    0.06
     nay
    0.06
    (item
    0.06
    оді
    0.06
    表情
    0.06
     зависит
    0.06
    нім
    0.06
     sne
    0.06
    -popup
    0.06
     căn
    0.06
    Act Density 0.011%

    No Known Activations