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

    Neuronpedia

    INDEX
    Explanations

    surprisingly cozy, very niche

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     उर्व
    0.39
     createArticle
    0.37
    เหล่า
    0.37
     oWord
    0.37
    વવા
    0.37
     custList
    0.37
     ARTICLE
    0.36
    ওয়া
    0.35
    ,*/}
    0.35
     لوا
    0.35
    POSITIVE LOGITS
     শৃ
    0.40
    rarse
    0.39
    ुकी
    0.39
    Fro
    0.38
     depre
    0.38
    name
    0.38
    Sadly
    0.37
    rantes
    0.37
     Saad
    0.37
    lista
    0.37
    Act Density 0.000%

    No Known Activations