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

    Neuronpedia

    INDEX
    Explanations

    broken nails

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     estar
    0.91
     respectivas
    0.90
    pción
    0.88
     wę
    0.87
     новой
    0.86
     стороны
    0.85
     ני
    0.84
     новая
    0.84
    ى
    0.84
     principais
    0.83
    POSITIVE LOGITS
    Attrition
    0.73
     ايجاد
    0.72
     marine
    0.71
     także
    0.71
    ('['
    0.71
     institute
    0.70
    聯盟
    0.70
     EPA
    0.69
    平日
    0.69
    我也是
    0.69
    Act Density 0.000%

    No Known Activations