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

    Neuronpedia

    INDEX
    Explanations

    with

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Coleman
    -0.07
     Colonial
    -0.06
     barracks
    -0.06
    (summary
    -0.06
     IQueryable
    -0.06
    เทพ
    -0.06
     Barker
    -0.06
    -tank
    -0.06
     guild
    -0.06
     bureauc
    -0.06
    POSITIVE LOGITS
    _sf
    0.06
     multinational
    0.06
    esteem
    0.06
    adb
    0.06
    (↵↵
    0.06
     Tasks
    0.06
     [&
    0.06
    _EM
    0.06
    _ATTRIBUTE
    0.06
    .conn
    0.06
    Act Density 0.048%

    No Known Activations