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

    Neuronpedia

    INDEX
    Explanations

    function

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Kostenlose
    -0.08
    /train
    -0.07
    _deps
    -0.07
     NSCoder
    -0.07
    俫
    -0.06
    ⒟
    -0.06
    .Lang
    -0.06
    ppv
    -0.06
    .Paint
    -0.06
     Madd
    -0.06
    POSITIVE LOGITS
    峙
    0.07
    চ
    0.07
     heated
    0.07
    ﮑ
    0.07
     Altern
    0.07
    液
    0.07
    ध
    0.07
    ヨ
    0.07
     world
    0.07
    GBT
    0.06
    Act Density 0.001%

    No Known Activations