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

    Neuronpedia

    INDEX
    Explanations

    publications

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Device
    -0.07
    payments
    -0.07
     mechanic
    -0.07
    了我的
    -0.07
    记忆力
    -0.07
    hari
    -0.06
    丝丝
    -0.06
    �
    -0.06
    -tools
    -0.06
     tabindex
    -0.06
    POSITIVE LOGITS
     feed
    0.06
    _suite
    0.06
     Merr
    0.06
     European
    0.06
     succes
    0.06
    (ct
    0.06
    ,np
    0.06
     ae
    0.06
     yür
    0.06
    סמ
    0.06
    Act Density 0.775%

    No Known Activations