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

    Neuronpedia

    INDEX
    Explanations

    positive future potential

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     sư
    0.69
    rifft
    0.67
    azier
    0.66
     জ্ঞ
    0.65
    riff
    0.62
    躾
    0.61
     परेश
    0.60
     berfungsi
    0.59
    yphenyl
    0.59
     otomatis
    0.59
    POSITIVE LOGITS
     promising
    3.62
     promise
    3.02
     encouraging
    2.73
     Promise
    2.61
     promet
    2.59
    promise
    2.53
     promises
    2.44
    Promise
    2.44
     promis
    2.40
     promesa
    2.15
    Act Density 0.341%

    No Known Activations