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

    Neuronpedia

    INDEX
    Explanations

    sharing private information

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     upaya
    0.44
    as
    0.43
    api
    0.43
     peraturan
    0.43
    one
    0.43
     one
    0.42
    anser
    0.40
     Ferris
    0.40
    an
    0.40
    at
    0.39
    POSITIVE LOGITS
     IDENTITY
    0.47
    ského
    0.46
    ské
    0.45
     വാർത്ത
    0.45
     cárc
    0.43
     intensify
    0.41
    は
    0.41
    ský
    0.41
    క
    0.41
    攝影
    0.40
    Act Density 0.017%

    No Known Activations