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

    Neuronpedia

    INDEX
    Explanations

    for prepositions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     আৰু
    0.83
     frameworks
    0.70
     आणि
    0.67
    ක්‍
    0.65
     therapists
    0.65
    ণ্ঠে
    0.64
     núcleos
    0.64
     contexts
    0.64
     minimalism
    0.64
    性和
    0.63
    POSITIVE LOGITS
    非常的
    0.70
     ocasion
    0.69
    。【
    0.68
    。
    0.68
     tohoto
    0.67
     alot
    0.66
    .[[
    0.66
    。<
    0.66
    。(
    0.65
     今回
    0.64
    Act Density 0.160%

    No Known Activations