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

    Neuronpedia

    INDEX
    Explanations

    c++ output and testing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ]-[
    0.76
     Bristol
    0.73
     Fabric
    0.72
    arnell
    0.72
    0.70
    гран
    0.70
    0.70
    ̓
    0.70
    _${
    0.69
    叄
    0.69
    POSITIVE LOGITS
     <<
    2.73
    <<
    2.34
     >>
    2.10
    >>
    1.95
    <<"
    1.88
    cout
    1.84
    )<<
    1.83
    ()<<
    1.82
     endl
    1.82
     <<"
    1.81
    Act Density 0.122%

    No Known Activations