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

    Neuronpedia

    INDEX
    Explanations

    legal and personal contexts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     راس
    0.43
    unu
    0.43
    ப்போது
    0.43
    baş
    0.42
    пень
    0.40
     ignore
    0.39
     })}
    0.39
     totalement
    0.39
    दिष्ट
    0.39
    radu
    0.38
    POSITIVE LOGITS
     Family
    0.47
     Elev
    0.41
    IBR
    0.41
    ēng
    0.40
     Les
    0.40
     Keeping
    0.40
     FAMILY
    0.40
     เพราะ
    0.40
     Staff
    0.39
     Guardians
    0.39
    Act Density 0.012%

    No Known Activations