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

    Neuronpedia

    INDEX
    Explanations

    professional followed by role

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    on
    1.34
    ا
    1.22
    AK
    1.09
    在
    1.08
    ले
    1.05
    am
    0.98
    مس
    0.98
    的技术
    0.98
    "
    0.97
     It
    0.96
    POSITIVE LOGITS
    ۰
    1.34
    <0x80>
    1.20
    st
    1.07
    ین
    1.07
    us
    1.05
    ad
    0.93
     professional
    0.93
     faceted
    0.93
     profesional
    0.92
    ๚
    0.90
    Act Density 0.031%

    No Known Activations