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

    Neuronpedia

    INDEX
    Explanations

    programming and crypto

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    মুখে
    0.39
    agliari
    0.39
    孢
    0.39
     renversement
    0.38
    嘹
    0.38
     ধ্বংস
    0.38
    <unused37>
    0.37
    搅拌
    0.37
     Shapiro
    0.36
    পূর্ণ
    0.35
    POSITIVE LOGITS
     file
    0.56
    file
    0.52
     files
    0.52
    files
    0.49
     фай
    0.48
     Android
    0.45
    ANDROID
    0.44
    fen
    0.43
    jan
    0.42
    fe
    0.42
    Act Density 0.000%

    No Known Activations