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

    Neuronpedia

    INDEX
    Explanations

    adult contexts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     a
    0.53
     अल्ट्रा
    0.46
    大使
    0.44
    浱
    0.44
     alebo
    0.42
    oelectric
    0.42
    ON
    0.41
    İlk
    0.41
    える
    0.41
    ボタン
    0.41
    POSITIVE LOGITS
    adult
    1.44
     adults
    1.42
     Adults
    1.42
     Adult
    1.41
    Adult
    1.41
     adult
    1.35
     adultes
    1.32
     adulta
    1.32
     взрослых
    1.30
     adulto
    1.29
    Act Density 0.048%

    No Known Activations