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

    Neuronpedia

    INDEX
    Explanations

    Afghan social issues

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     lại
    0.46
     zapewnia
    0.45
    Repos
    0.45
     luôn
    0.44
     selama
    0.43
     또한
    0.43
     selalu
    0.42
    કમાં
    0.42
     sürekli
    0.42
     प्रदान
    0.41
    POSITIVE LOGITS
     десятки
    0.44
     Afghan
    0.43
     warned
    0.43
     PTSD
    0.42
     mesela
    0.42
    ですから
    0.41
    overty
    0.41
     begy
    0.40
     Afghans
    0.40
     ourselves
    0.40
    Act Density 0.011%

    No Known Activations