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

    Neuronpedia

    INDEX
    Explanations

    foreign language America identification

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    året
    0.50
    êtes
    0.49
    гах
    0.45
    zić
    0.44
    ples
    0.44
     دو
    0.44
     chambre
    0.43
    zele
    0.43
    ول
    0.42
    uras
    0.41
    POSITIVE LOGITS
     Crusade
    0.49
     അമേരിക്ക
    0.49
    REW
    0.46
     deniz
    0.46
     미국
    0.45
     AMERICA
    0.45
     മുതല്‍
    0.45
    전
    0.45
     ameryka
    0.44
    あなたは
    0.44
    Act Density 0.004%

    No Known Activations