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

    Neuronpedia

    INDEX
    Explanations

    >

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Sin
    -0.07
    仅
    -0.06
    青
    -0.06
     holiday
    -0.06
     Phar
    -0.06
    arnings
    -0.06
    pac
    -0.06
    criptions
    -0.06
    -render
    -0.06
    能力
    -0.05
    POSITIVE LOGITS
     rollback
    0.07
    >A
    0.07
    29
    0.06
     robbed
    0.06
    mobx
    0.06
     tụ
    0.06
     выбира
    0.06
     **/
↵
    0.06
    STORE
    0.06
    WF
    0.06
    Act Density 0.004%

    No Known Activations