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

    Neuronpedia

    INDEX
    Explanations

    following "in" or "including"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    AboutDlg
    0.39
    átky
    0.38
    而已
    0.36
    قتصاد
    0.34
    ዊ
    0.34
    creas
    0.34
    تمع
    0.33
     girdi
    0.33
    รษฐกิจ
    0.33
     públicas
    0.33
    POSITIVE LOGITS
    睉
    0.40
     בו
    0.37
    boo
    0.36
    Stern
    0.36
    గ్ర
    0.36
     ವಿಧಾನಸ
    0.35
    DING
    0.35
    咅
    0.35
     अधिकार
    0.35
    Nord
    0.34
    Act Density 0.006%

    No Known Activations