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

    Neuronpedia

    INDEX
    Explanations

    landmark achievement, navigation, categories

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     as
    1.44
    that
    1.02
    t
    0.96
    什么
    0.90
    Loading
    0.90
    u
    0.89
    Json
    0.89
    يل
    0.86
     \[
    0.86
    l
    0.86
    POSITIVE LOGITS
     landmarks
    1.33
     landmark
    1.24
    '
    1.21
    landmark
    1.15
    م
    1.13
    landmarks
    1.11
    جی
    1.02
     arbres
    0.98
     የሆነ
    0.97
    omers
    0.95
    Act Density 0.002%

    No Known Activations