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

    Neuronpedia

    INDEX
    Explanations

    pleasure honor privilege

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    要注意
    0.39
    👎
    0.38
     buttery
    0.38
     mocking
    0.37
    Yep
    0.37
     উঠিল
    0.36
    orestation
    0.36
    してた
    0.36
     hardcore
    0.35
    realistic
    0.35
    POSITIVE LOGITS
     privilege
    2.45
     privil
    2.05
     Privilege
    2.05
     privileged
    2.02
     privileges
    2.00
     privilegio
    2.00
     privile
    1.83
     privilegi
    1.77
    Priv
    1.75
     pleasure
    1.72
    Act Density 0.023%

    No Known Activations