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

    Neuronpedia

    INDEX
    Explanations

    how to use

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     I
    0.53
    cd
    0.50
     wander
    0.44
    chen
    0.43
    Ты
    0.43
     lawyers
    0.43
     lawyer
    0.42
     magn
    0.42
     ombre
    0.42
    **
    0.41
    POSITIVE LOGITS
     استخدم
    0.49
     استعمال
    0.46
     использова
    0.46
     effettuare
    0.45
     જે
    0.44
     utilizan
    0.44
     उपयोग
    0.43
     mecz
    0.41
    使用
    0.40
     используются
    0.40
    Act Density 0.012%

    No Known Activations