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

    Neuronpedia

    INDEX
    Explanations

    or other options

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    الب
    0.47
    这些
    0.45
     تلك
    0.43
     perjury
    0.43
    وني
    0.43
     luchar
    0.43
     conundrum
    0.41
     murderous
    0.41
     aceste
    0.41
     miserably
    0.40
    POSITIVE LOGITS
    或
    0.44
    或其他
    0.44
     intentionally
    0.43
    either
    0.41
    defined
    0.41
    iegend
    0.41
     அல்லது
    0.41
     either
    0.40
    umers
    0.40
    াহিনীর
    0.40
    Act Density 0.520%

    No Known Activations