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

    Neuronpedia

    INDEX
    Explanations

    debunking myths

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    г
    1.50
    {},
    1.29
    𝚜
    1.29
    yzed
    1.28
     nhiên
    1.25
    #{
    1.25
    𝓼
    1.24
    дің
    1.23
    catalyzed
    1.23
    ilities
    1.22
    POSITIVE LOGITS
    d
    1.48
    ្នក
    1.41
    ang
    1.34
    न
    1.23
     dizziness
    1.20
    ols
    1.14
    ிரி
    1.14
     doorbell
    1.14
     codon
    1.13
     Rumah
    1.13
    Act Density 0.002%

    No Known Activations