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

    Neuronpedia

    INDEX
    Explanations

    future intentions or plans

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     hinzufügen
    0.72
     रिमाइंडर
    0.67
     أيضًا
    0.64
     Нужно
    0.64
     újra
    0.63
     También
    0.63
     cloudinary
    0.62
     sentimientos
    0.62
     también
    0.61
     दोबारा
    0.61
    POSITIVE LOGITS
     promised
    1.44
     hoped
    1.23
    promised
    1.17
     expected
    1.13
     intended
    1.13
     promise
    1.11
     planned
    1.05
    expected
    1.05
     predicted
    1.00
     anticipated
    0.98
    Act Density 0.000%

    No Known Activations