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

    Neuronpedia

    INDEX
    Explanations

    Robin boundary conditions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    öv
    -0.90
    cionales
    -0.87
    DataAccess
    -0.83
    chapel
    -0.82
    Mär
    -0.81
    ảnh
    -0.80
    теле
    -0.79
    зак
    -0.79
     reise
    -0.79
     ویکی‌پدیای
    -0.79
    POSITIVE LOGITS
     illustrating
    0.91
    ILS
    0.89
    OE
    0.88
    lowed
    0.86
    arriver
    0.84
     INCREASE
    0.84
     examples
    0.83
    <h3>
    0.83
    increase
    0.82
     Allows
    0.82
    Act Density 0.045%

    No Known Activations