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

    Neuronpedia

    INDEX
    Explanations

    a followed by a specific descriptor

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     approximately
    0.18
     considerably
    0.18
    <0xE2>
    0.17
     extremely
    0.16
     substantially
    0.16
     quite
    0.16
     extensively
    0.15
     상당히
    0.15
     [(
    0.15
     the
    0.15
    POSITIVE LOGITS
     solche
    0.18
     vraie
    0.18
     solchen
    0.18
     dodgy
    0.17
     lefty
    0.17
     crappy
    0.17
     sinner
    0.17
     glimpse
    0.17
     hunch
    0.17
     οπο
    0.16
    Act Density 0.481%

    No Known Activations