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

    Neuronpedia

    INDEX
    Explanations

    observation, stimulating, salt, noisy, pixel

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Tam
    0.39
     Party
    0.39
     ammonia
    0.38
    踞
    0.38
     dolor
    0.38
    Toronto
    0.38
    packages
    0.36
     Dhan
    0.36
     Ammonia
    0.36
     wrap
    0.35
    POSITIVE LOGITS
     المؤمن
    0.40
     высо
    0.39
    ایید
    0.39
    ля
    0.38
     naïve
    0.38
    mild
    0.38
     waivers
    0.38
    ूबी
    0.38
     waiver
    0.38
    enregist
    0.38
    Act Density 0.004%

    No Known Activations