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

    Neuronpedia

    INDEX
    Explanations

    dependency injection and beans

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ُر
    0.62
    回归
    0.61
     récentes
    0.60
     réduction
    0.60
    មក
    0.60
     représentent
    0.60
    ión
    0.59
    女
    0.59
     rangement
    0.59
     sparsely
    0.58
    POSITIVE LOGITS
     for
    0.93
    ת
    0.87
    תה
    0.82
     as
    0.70
    ल
    0.70
    ้
    0.67
    ل
    0.66
    ت
    0.66
    וה
    0.64
    ল
    0.64
    Act Density 0.002%

    No Known Activations