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

    Neuronpedia

    INDEX
    Explanations

    rare and challenged concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    اليا
    0.48
    ﻔ
    0.45
    ylmethylsulfanyl
    0.44
    라마
    0.44
    ﻜ
    0.43
    constraintStart
    0.42
    일
    0.42
     CaCO
    0.42
    IERC
    0.40
    साय
    0.40
    POSITIVE LOGITS
    dings
    0.45
     خواهند
    0.44
     বে
    0.44
     سین
    0.44
     Ren
    0.43
     تمہیں
    0.43
     بھارت
    0.42
     Official
    0.42
    㳓
    0.42
     manuals
    0.41
    Act Density 0.004%

    No Known Activations