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

    Neuronpedia

    INDEX
    Explanations

    barangays

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    推理
    0.41
     aer
    0.39
     aero
    0.39
     의료
    0.38
    bro
    0.37
    ິ່ງ
    0.36
     Tox
    0.36
    દર
    0.36
     Ammonia
    0.36
     जहर
    0.36
    POSITIVE LOGITS
    DateTimeField
    0.41
     Mayer
    0.40
     bringen
    0.38
    萺
    0.37
    Phantom
    0.37
    Listing
    0.36
    ੌ
    0.36
    ಡೆ
    0.35
    িমা
    0.35
    View
    0.35
    Act Density 0.000%

    No Known Activations