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

    Neuronpedia

    INDEX
    Explanations

    source

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ène
    -0.30
    è¹Ĭ
    -0.28
    .Constant
    -0.26
    ç½ijç«Ļé¦ĸ页
    -0.26
    enez
    -0.26
    ä¸Ģé¢Ĺ
    -0.26
    bef
    -0.25
     SHALL
    -0.25
     dependent
    -0.25
    .defineProperty
    -0.24
    POSITIVE LOGITS
    dings
    0.30
     Rc
    0.27
    liches
    0.26
    gency
    0.26
    èħ¹
    0.26
    _rc
    0.25
     ÐĽÐ¸
    0.25
    water
    0.24
    XD
    0.24
    emale
    0.24
    Act Density 0.275%

    No Known Activations