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

    Neuronpedia

    INDEX
    Explanations

    URL list identifiers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     pear
    -0.07
    .cl
    -0.07
    Pas
    -0.07
     Sur
    -0.07
    浑
    -0.06
    -per
    -0.06
     Ef
    -0.06
     서울
    -0.06
    %/
    -0.06
     Brenda
    -0.06
    POSITIVE LOGITS
    ATRIX
    0.07
     ResourceType
    0.07
    getExtension
    0.07
     Enforcement
    0.07
     Johannes
    0.07
    了一批
    0.07
     Rank
    0.07
    انخفاض
    0.07
    picable
    0.07
    ReLU
    0.07
    Act Density 0.003%

    No Known Activations