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

    Neuronpedia

    INDEX
    Explanations

    Code output and answers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ta
    1.66
    to
    1.56
    ă
    1.50
     soff
    1.47
     kerk
    1.46
     wojewód
    1.45
    um
    1.44
    Д
    1.40
    সঙ্গত
    1.39
     ported
    1.39
    POSITIVE LOGITS
    یتی
    1.58
    uwa
    1.42
     پت
    1.39
     використання
    1.38
    тие
    1.37
    quels
    1.33
     হ্যাঁ
    1.33
    𝐼
    1.32
    ्वती
    1.32
    हरे
    1.32
    Act Density 0.000%

    No Known Activations