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

    Neuronpedia

    INDEX
    Explanations

    groups of people

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    اخ
    0.37
     pains
    0.36
     зла
    0.36
    حت
    0.36
     Newell
    0.35
     Gober
    0.34
     সত্ব
    0.34
     süreç
    0.34
    рк
    0.34
     sürec
    0.34
    POSITIVE LOGITS
     tro
    0.70
    Tro
    0.60
     troup
    0.59
    尤其是
    0.58
     Troop
    0.58
    tro
    0.57
     Tro
    0.57
     troop
    0.55
    troop
    0.55
     TRO
    0.51
    Act Density 0.001%

    No Known Activations