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

    Neuronpedia

    INDEX
    Explanations

    XML specification URLs

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (table
    -0.07
     dentist
    -0.07
     thao
    -0.07
     Welfare
    -0.07
    OUNTRY
    -0.07
     труда
    -0.07
     Đối
    -0.07
    afety
    -0.07
    .aw
    -0.07
    antaged
    -0.07
    POSITIVE LOGITS
    /XML
    0.09
    /spec
    0.09
    /xml
    0.07
    Prosec
    0.07
     ／:
    0.06
    ')";↵
    0.06
     빠
    0.06
     communicating
    0.06
     irrit
    0.06
     professionalism
    0.06
    Act Density 0.000%

    No Known Activations