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

    Neuronpedia

    INDEX
    Explanations

    sound verbs and foreign words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     дуже
    0.45
    憾
    0.44
    ƈ
    0.43
     যেহেতু
    0.42
     giants
    0.42
    その他
    0.41
     seasonality
    0.41
     ძალიან
    0.41
     सरकार
    0.40
     tragedies
    0.40
    POSITIVE LOGITS
     ihn
    0.50
    ő
    0.48
     från
    0.47
     detener
    0.45
    an
    0.44
     her
    0.44
     bellow
    0.43
     métallique
    0.43
    ه
    0.42
    istern
    0.42
    Act Density 0.657%

    No Known Activations