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

    Neuronpedia

    INDEX
    Explanations

    xml preamble

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    eclampsia
    0.41
    E
    0.40
    pexels
    0.38
    unsplash
    0.38
    僭
    0.38
    endig
    0.37
     marin
    0.36
    effectively
    0.36
    Container
    0.36
    arming
    0.36
    POSITIVE LOGITS
     "}
    0.45
    }`
    0.44
    bf
    0.44
    ?}
    0.42
    刋
    0.42
     fontFamily
    0.40
     부터
    0.40
     //}
    0.40
    #}
    0.39
     teamTable
    0.39
    Act Density 0.003%

    No Known Activations