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

    Neuronpedia

    INDEX
    Explanations

    languages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    foam
    0.65
     foam
    0.63
    Macrophages
    0.62
     cogeneration
    0.60
     cAMP
    0.60
     apopt
    0.60
    ⢿
    0.60
     小物
    0.59
    消防
    0.59
     fabs
    0.58
    POSITIVE LOGITS
     languages
    3.57
     language
    3.49
     Language
    3.22
     Languages
    3.20
    Language
    3.19
     bahasa
    3.13
    language
    3.04
    语言
    3.03
    Languages
    2.97
     idioma
    2.96
    Act Density 2.132%

    No Known Activations