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

    Neuronpedia

    INDEX
    Explanations

    (

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ////
    -0.07
     impeachment
    -0.06
    ght
    -0.06
    _Response
    -0.06
    _BACK
    -0.06
    _runtime
    -0.06
    ╗
    -0.06
     tyto
    -0.06
     خواب
    -0.06
    ský
    -0.06
    POSITIVE LOGITS
     manus
    0.07
     """
↵
↵
    0.06
     فرآ
    0.06
    раж
    0.06
     LEDs
    0.06
     بايد
    0.06
    sett
    0.06
    /ip
    0.06
     pwd
    0.06
    Currently
    0.06
    Act Density 0.005%

    No Known Activations