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

    Neuronpedia

    INDEX
    Explanations

    examples of concepts or types

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     więc
    0.37
     najleps
    0.36
     najważ
    0.34
     prawdzi
    0.33
     yüzden
    0.33
     deswegen
    0.33
     çünkü
    0.32
     Đây
    0.32
     unapolog
    0.32
     kavram
    0.31
    POSITIVE LOGITS
    也可以
    0.48
    也有
    0.45
    某些
    0.44
    的一些
    0.40
     similarly
    0.39
     থেকেও
    0.38
    ლებიც
    0.37
     মধ্যেও
    0.37
    也能
    0.37
    也會
    0.37
    Act Density 0.051%

    No Known Activations