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

    Neuronpedia

    INDEX
    Explanations

    international trade

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    0.50
     dilihat
    0.45
     to
    0.45
    An
    0.45
     word
    0.44
     <
    0.43
     behind
    0.43
     runway
    0.43
     Bl
    0.42
     Runway
    0.42
    POSITIVE LOGITS
    𝖑
    0.58
    ensureEqual
    0.57
    branchNode
    0.57
    echolog
    0.56
    лайн
    0.55
    𝚛
    0.55
     auxqu
    0.54
     atthakath
    0.54
     lymphatiques
    0.54
    wallepics
    0.52
    Act Density 0.000%

    No Known Activations