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

    Neuronpedia

    INDEX
    Explanations

    public class

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     This
    1.05
     f
    1.02
     l
    1.00
     m
    0.97
    <0x0D>
    0.96
     this
    0.96
     However
    0.95
     k
    0.94
     t
    0.91
     In
    0.91
    POSITIVE LOGITS
    У
    1.18
    𝓙
    1.02
    ഐ
    1.01
    С
    1.00
    ی
    0.99
    页面存档备份
    0.98
    Emple
    0.96
    А
    0.96
    Football
    0.96
    kotlin
    0.95
    Act Density 0.006%

    No Known Activations