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

    Neuronpedia

    INDEX
    Explanations

    O(n)

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     chunky
    0.84
     bevel
    0.83
    NavigationView
    0.83
     Boulevard
    0.82
     Obesity
    0.81
    Ւ
    0.80
     Lomond
    0.80
    なっている
    0.80
    昻
    0.79
     ~/.
    0.79
    POSITIVE LOGITS
    ا
    0.95
    ни
    0.94
    enso
    0.91
    荅
    0.89
    イス
    0.88
     racines
    0.87
    lime
    0.86
    आ
    0.85
    enze
    0.83
    ่
    0.83
    Act Density 0.000%

    No Known Activations