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

    Neuronpedia

    INDEX
    Explanations

    code and filenames

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    BOSE
    -0.06
    配
    -0.06
    EMBER
    -0.06
    OURCE
    -0.06
    Mutable
    -0.06
    EMA
    -0.06
     >↵
    -0.06
    eated
    -0.06
    ール
    -0.06
     sequences
    -0.06
    POSITIVE LOGITS
     forControlEvents
    0.07
    一直
    0.07
     세계
    0.07
    tfoot
    0.06
     vuông
    0.06
    orny
    0.06
    /graphql
    0.06
    ,NULL
    0.06
     ني
    0.06
    -trade
    0.06
    Act Density 0.027%

    No Known Activations