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

    Neuronpedia

    INDEX
    Explanations

    context and surrounding text

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ح
    0.51
    зай
    0.50
    the
    0.49
    ghi
    0.49
    ه
    0.46
    Dental
    0.45
    qu
    0.44
    migration
    0.44
    meaning
    0.44
    тал
    0.43
    POSITIVE LOGITS
     baños
    0.54
     są
    0.48
     เอ่อ
    0.48
    finaly
    0.44
     Abbiamo
    0.44
     Якщо
    0.43
    .`);
    0.43
     poté
    0.42
     cultivos
    0.42
    ]=-
    0.42
    Act Density 0.004%

    No Known Activations