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

    Neuronpedia

    INDEX
    Explanations

    name and with Screen

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    0.39
    inko
    0.39
     দেখা
    0.38
     দিবস
    0.38
    Reason
    0.37
     مشر
    0.37
     Kendrick
    0.37
    ぢ
    0.37
    েন্দ্রনাথ
    0.36
    гре
    0.36
    POSITIVE LOGITS
     release
    0.39
     dabei
    0.39
    破損
    0.38
     computer
    0.37
     പ്രധാന
    0.37
     corpus
    0.37
    iella
    0.37
    PELL
    0.36
     releasing
    0.35
     continuing
    0.35
    Act Density 0.000%

    No Known Activations