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

    Neuronpedia

    INDEX
    Explanations

    assistant greetings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Archer
    -0.09
     dart
    -0.09
    ForKey
    -0.08
    uhe
    -0.08
    ivot
    -0.08
    uh
    -0.08
     Staples
    -0.08
    inheritDoc
    -0.08
    .tc
    -0.08
     cryst
    -0.08
    POSITIVE LOGITS
     you
    0.23
    ä½ł
    0.19
     youre
    0.19
    you
    0.17
     bạn
    0.15
    You
    0.15
     você
    0.14
     vous
    0.14
    æĤ¨
    0.14
     perhaps
    0.13
    Act Density 0.258%

    No Known Activations