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

    Neuronpedia

    INDEX
    Explanations

    office details and roles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    رك
    1.07
    re
    0.96
    ت
    0.96
    на
    0.93
    ार
    0.92
     ס
    0.92
     in
    0.91
     स
    0.90
    在
    0.90
     यूज
    0.88
    POSITIVE LOGITS
    <0x80>
    1.48
    0
    1.37
    :
    1.33
    ０
    1.16
    is
    1.14
    í
    1.13
    ۰
    1.05
    ;
    1.02
    ，
    0.98
     Office
    0.96
    Act Density 0.005%

    No Known Activations