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

    Neuronpedia

    INDEX
    Explanations

    clothing and accessories

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ul
    1.11
    면
    1.00
    nya
    0.99
    ,
    0.96
    us
    0.91
    zelfde
    0.90
    s
    0.87
    च्या
    0.84
     UHF
    0.79
     Balkans
    0.78
    POSITIVE LOGITS
    ي
    1.36
    י
    1.30
    лу
    1.23
     gloves
    1.19
    ↵
    1.17
    ф
    1.07
    O
    1.06
     Gloves
    1.05
    נ
    1.04
    м
    1.02
    Act Density 0.004%

    No Known Activations