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

    Neuronpedia

    INDEX
    Explanations

    stage, changes, window, tab

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Kal
    0.39
    ומי
    0.39
     infusions
    0.38
     bund
    0.38
    骨
    0.37
    Stone
    0.37
    லு
    0.37
     Emery
    0.37
     infusion
    0.36
     Stone
    0.36
    POSITIVE LOGITS
     window
    0.50
     Changes
    0.50
     stage
    0.48
     changes
    0.47
     staged
    0.47
     ট্যাব
    0.47
     tab
    0.46
    タブ
    0.46
     Window
    0.46
    窗口
    0.45
    Act Density 0.005%

    No Known Activations