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

    Neuronpedia

    INDEX
    Explanations

    does not constitute medical advice

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     генера
    0.39
    ون
    0.36
     chacune
    0.36
    なのか
    0.34
    featuresMatrix
    0.34
    ত
    0.34
     месту
    0.33
    মেন্ট
    0.33
     молодых
    0.33
     явления
    0.33
    POSITIVE LOGITS
     ذریع
    0.36
     it
    0.35
     It
    0.32
     którego
    0.31
     pharmacists
    0.30
    它可以
    0.29
     filmmakers
    0.28
     ہیں۔
    0.28
     എന്നിവ
    0.27
     baut
    0.27
    Act Density 0.083%

    No Known Activations