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

    Neuronpedia

    INDEX
    Explanations

    counter narrative, IT Admin, project SAVE

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    𝖽
    0.43
    }')
    0.41
     اخذنا
    0.41
    cPix
    0.39
    形成
    0.38
    批准
    0.37
     ZOOM
    0.37
    或是
    0.37
    汥
    0.37
     شفنا
    0.36
    POSITIVE LOGITS
     patru
    0.48
     зая
    0.47
     آپریشن
    0.45
     tentang
    0.44
     मुझ
    0.44
     moja
    0.43
     acht
    0.43
     मेरी
    0.43
     Mers
    0.43
     நான்கு
    0.42
    Act Density 0.010%

    No Known Activations