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

    Neuronpedia

    INDEX
    Explanations

    void main

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    就不
    0.36
    Beginning
    0.36
    chanics
    0.36
    kind
    0.35
    ]").
    0.35
    ">*
    0.35
    sup
    0.35
    esse
    0.34
     सुप
    0.34
    usik
    0.34
    POSITIVE LOGITS
     main
    0.91
    main
    0.69
     основные
    0.64
     основной
    0.63
     utama
    0.61
     основ
    0.61
    主な
    0.59
    主要的
    0.59
     główn
    0.58
     основных
    0.57
    Act Density 0.006%

    No Known Activations