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

    Neuronpedia

    INDEX
    Explanations

    current growth potential

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     uni
    0.46
     Canadian
    0.45
     he
    0.43
     canadian
    0.41
     captivated
    0.41
     red
    0.40
     mid
    0.40
     CDN
    0.40
     l
    0.40
     poziom
    0.40
    POSITIVE LOGITS
    槭
    0.48
    Dys
    0.47
     کرد
    0.46
    wać
    0.46
    शुल्क
    0.45
     რომელი
    0.45
    क्ष्य
    0.44
    는데
    0.44
    Emple
    0.43
    Packages
    0.43
    Act Density 0.000%

    No Known Activations