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

    Neuronpedia

    INDEX
    Explanations

    engaging community

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Tweet
    1.06
     commas
    1.00
    PRI
    0.97
    Cookie
    0.96
    दा
    0.94
    Ț
    0.93
    Domain
    0.93
     einzelnen
    0.93
    Genre
    0.91
    τες
    0.90
    POSITIVE LOGITS
    subunit
    1.12
     подготовки
    1.08
    verständ
    1.06
    inputStream
    1.06
     constructively
    1.04
    ውን
    1.03
    峹
    1.02
     persiapan
    1.02
    激发
    1.01
     passionately
    1.01
    Act Density 0.000%

    No Known Activations