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

    Neuronpedia

    INDEX
    Explanations

    code snippets and technical formats

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Đối
    0.77
    acetamol
    0.76
     isoforms
    0.76
     İlk
    0.74
     Manoj
    0.72
    elementAt
    0.71
     alloying
    0.69
     alrededores
    0.68
     inventors
    0.68
     Deuteronomy
    0.68
    POSITIVE LOGITS
    ton
    0.78
    $
    0.77
    $">
    0.76
    Boogie
    0.75
    िया
    0.75
     conex
    0.75
    數位
    0.75
     счета
    0.73
     sogno
    0.73
    .${
    0.72
    Act Density 0.004%

    No Known Activations