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

    Neuronpedia

    INDEX
    Explanations

    nullish coalescing operator `??`

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     can
    1.13
     are
    1.01
    ized
    1.00
     it
    0.94
     of
    0.89
    t
    0.87
     for
    0.81
     we
    0.80
     at
    0.80
    I
    0.80
    POSITIVE LOGITS
    ের
    0.96
    ו
    0.89
    지
    0.86
    ాన్
    0.84
    ल
    0.84
    도
    0.83
    ا
    0.81
    なった
    0.80
    な
    0.79
    ל
    0.79
    Act Density 0.044%

    No Known Activations