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

    Neuronpedia

    INDEX
    Explanations

    home to X

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     جیسے
    0.73
     وړیا
    0.73
     ভোগের
    0.73
     אבל
    0.72
    aminen
    0.70
     הולנד
    0.69
    זרה
    0.69
    projects
    0.69
     стр
    0.68
     kullan
    0.68
    POSITIVE LOGITS
     birthplace
    1.45
     headquarters
    1.19
     célèbre
    1.12
     of
    1.10
     famed
    1.02
     home
    1.01
     Birth
    0.98
     famous
    0.98
    Birth
    0.93
     Headquarters
    0.93
    Act Density 0.050%

    No Known Activations