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

    Neuronpedia

    INDEX
    Explanations

    foreign scripts and diverse topics

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     marvell
    0.47
     paragon
    0.46
     astronom
    0.46
     Far
    0.45
     Farah
    0.45
     Web
    0.44
     sombre
    0.44
     web
    0.43
     Port
    0.43
     glimmer
    0.43
    POSITIVE LOGITS
    illation
    0.54
    צא
    0.51
    𝙛
    0.50
    sna
    0.47
    retreat
    0.47
    elijk
    0.46
     кү
    0.46
     মুনা
    0.46
    ಯೇ
    0.46
    iesią
    0.46
    Act Density 0.001%

    No Known Activations