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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Mahmoud
    -0.08
    ne
    -0.07
     swe
    -0.07
     ATA
    -0.07
    心理
    -0.06
     hos
    -0.06
    anford
    -0.06
     hostage
    -0.06
    pageSize
    -0.06
    ร
    -0.06
    POSITIVE LOGITS
    .");↵
    0.07
     검색
    0.07
     Wealth
    0.07
    지역
    0.07
    lič
    0.06
    ��
    0.06
    ?)↵↵
    0.06
    Dims
    0.06
    ("/")↵
    0.06
     발표
    0.06
    Act Density 0.037%

    No Known Activations