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

    Neuronpedia

    INDEX
    Explanations

    verb infinitive + pronoun

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     त्याने
    0.46
     त्यांनी
    0.43
    に示す
    0.43
     చేశాడు
    0.41
    Gauche
    0.40
     உண்டு
    0.39
     SHF
    0.39
    ༺
    0.39
     করতে
    0.38
     தமது
    0.38
    POSITIVE LOGITS
    iénd
    0.86
    arlo
    0.76
    ándolo
    0.75
    irlo
    0.73
    adlo
    0.68
    idlo
    0.66
    arlos
    0.63
    ându
    0.61
     તેને
    0.59
    把它
    0.59
    Act Density 0.021%

    No Known Activations