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

    Neuronpedia

    INDEX
    Explanations

    relationship building, interactive slider

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     астро
    0.52
    iftung
    0.48
     చర్య
    0.43
     груп
    0.41
    сна
    0.41
    ి
    0.41
    傥
    0.41
     прямо
    0.40
    ጶ
    0.40
     Astr
    0.40
    POSITIVE LOGITS
    sp
    0.45
    og
    0.45
     this
    0.44
     Rass
    0.40
     officia
    0.39
     spread
    0.39
    YO
    0.38
     dalje
    0.38
     sowas
    0.38
     Algeria
    0.37
    Act Density 0.001%

    No Known Activations