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
    .ActionEvent
    -0.07
    (Menu
    -0.07
    _PH
    -0.07
     формирова
    -0.07
    这样做
    -0.07
     created
    -0.07
     Eisen
    -0.07
     mov
    -0.06
     TOK
    -0.06
    的问题
    -0.06
    POSITIVE LOGITS
    xt
    0.07
     uLocal
    0.06
     בשב
    0.06
    限量
    0.06
    圹
    0.06
    祗
    0.06
     sıcak
    0.06
    عاط
    0.06
    life
    0.06
    شغل
    0.06
    Act Density 0.047%

    No Known Activations