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

    Neuronpedia

    INDEX
    Explanations

    code, technical language

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     contrasting
    -0.07
    advert
    -0.06
    _pv
    -0.06
     occurrences
    -0.06
    .scheme
    -0.06
    HEADER
    -0.06
    _bm
    -0.06
     globe
    -0.06
    <quote
    -0.06
    ottesville
    -0.06
    POSITIVE LOGITS
    technical
    0.07
     Clone
    0.06
    افية
    0.06
     discipline
    0.06
     Trudeau
    0.06
     mongoose
    0.06
    ounds
    0.06
     Union
    0.06
    .Categories
    0.06
    DW
    0.06
    Act Density 0.000%

    No Known Activations