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

    Neuronpedia

    INDEX
    Explanations

    what you explore

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    four
    0.94
     three
    0.91
    six
    0.89
     corrective
    0.88
     seven
    0.88
     Decode
    0.88
     Hunting
    0.87
     four
    0.87
     Start
    0.86
     enzymatic
    0.86
    POSITIVE LOGITS
    ț
    0.88
    hrt
    0.87
     riêng
    0.86
    يع
    0.85
    ્ઞ
    0.85
     igény
    0.82
     மக்கள
    0.82
    kern
    0.81
     स्वयं
    0.81
    देशीर
    0.81
    Act Density 0.260%

    No Known Activations