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

    Neuronpedia

    INDEX
    Explanations

    compiler, cpp, coordinates

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     डायब
    0.39
     utilization
    0.39
     игровые
    0.39
     দখ
    0.38
    邀
    0.38
    िक
    0.37
     дә
    0.37
     ऑर्गे
    0.36
    山区
    0.36
     diab
    0.36
    POSITIVE LOGITS
    cpp
    0.40
    unki
    0.40
     confidence
    0.38
    Fused
    0.38
    compiler
    0.37
     highlighting
    0.37
    led
    0.37
    idis
    0.37
     resembling
    0.36
    GCC
    0.36
    Act Density 0.000%

    No Known Activations