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

    Neuronpedia

    INDEX
    Explanations

    URL paths and file names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     abel
    -0.84
    њ
    -0.80
    nigh
    -0.78
     támogat
    -0.77
     بح
    -0.76
     foncé
    -0.75
    دان
    -0.75
    の記事
    -0.74
     enable
    -0.73
    mongoose
    -0.73
    POSITIVE LOGITS
    ೮
    0.83
     یو
    0.82
     אית
    0.77
     drzwi
    0.76
     کشت
    0.74
    อิง
    0.72
     Utd
    0.72
    usak
    0.72
     PriorityQueue
    0.72
     supposed
    0.71
    Act Density 0.001%

    No Known Activations