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

    Neuronpedia

    INDEX
    Explanations

    graphics card model numbers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     RTX
    0.52
    RTC
    0.47
    RT
    0.45
     rtn
    0.45
    ∞
    0.44
     धान
    0.44
    Rt
    0.44
    rt
    0.43
     RT
    0.42
    绮
    0.41
    POSITIVE LOGITS
     Marion
    0.48
    Marion
    0.45
     OC
    0.44
     bit
    0.41
     Sist
    0.38
     Fairy
    0.38
    Faction
    0.37
     test
    0.37
     Us
    0.36
     Test
    0.36
    Act Density 0.012%

    No Known Activations