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

    Neuronpedia

    INDEX
    Explanations

    light bulb

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    و
    2.16
    ت
    2.16
    ט
    2.11
    л
    2.09
    ו
    2.09
    י
    2.06
    ות
    2.03
    ים
    1.98
    υ
    1.93
    ת
    1.91
    POSITIVE LOGITS
     Microscope
    1.44
    (
    1.41
    "
    1.38
     economical
    1.37
    的工作
    1.34
     suspect
    1.33
     glance
    1.30
     percept
    1.30
    1.28
     tension
    1.27
    Act Density 0.002%

    No Known Activations