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

    Neuronpedia

    INDEX
    Explanations

    describes parts or states

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ੩
    0.52
    زء
    0.45
    ੪
    0.45
    সংখ্য
    0.44
    蔑
    0.44
    ్యాచ్
    0.44
    videmment
    0.43
    घव
    0.43
    infeld
    0.42
    ospels
    0.42
    POSITIVE LOGITS
     cho
    0.55
     để
    0.54
     sẻ
    0.53
     मि
    0.50
     Cho
    0.48
     του
    0.48
    G
    0.47
     بی
    0.46
     Tale
    0.46
     Ch
    0.45
    Act Density 0.001%

    No Known Activations