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

    Neuronpedia

    INDEX
    Explanations

    breakdown or reasons

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     %``
    0.45
    reflectionCamera
    0.41
     another
    0.38
     passwords
    0.38
     другая
    0.38
    ণ্
    0.37
    television
    0.37
     stirrer
    0.37
    ᱪ
    0.37
     icon
    0.37
    POSITIVE LOGITS
     både
    0.50
     především
    0.47
     kontinuier
    0.47
     दरअसल
    0.45
     głównie
    0.45
     प्रचंड
    0.44
     zowel
    0.43
     principalmente
    0.43
    primarily
    0.43
     süreç
    0.43
    Act Density 0.521%

    No Known Activations