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

    Neuronpedia

    INDEX
    Explanations

    Nose

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    emens
    -0.28
    åİŁèijĹ
    -0.28
    人éĢī
    -0.26
    ÂŃi
    -0.26
     volte
    -0.26
    /legal
    -0.25
    éĢı
    -0.25
     publi
    -0.25
    é«ĺçŃī
    -0.25
    iminal
    -0.24
    POSITIVE LOGITS
    ald
    0.29
    æ°ª
    0.27
     concurrent
    0.26
    cert
    0.26
    å¿Į
    0.26
    èĢĥ
    0.25
    каÑĤ
    0.25
     season
    0.25
    on
    0.25
    Setting
    0.24
    Act Density 0.028%

    No Known Activations