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

    Neuronpedia

    INDEX
    Explanations

    console logging

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ചര്യ
    0.91
     nạn
    0.81
     አማ
    0.81
    hattan
    0.81
    bfs
    0.81
     getline
    0.80
    Ⲙ
    0.80
    |।
    0.80
     getText
    0.80
    donald
    0.79
    POSITIVE LOGITS
    log
    1.03
     log
    0.94
     Log
    0.79
    Log
    0.69
     table
    0.68
     logs
    0.67
     logarithms
    0.67
    ሎ
    0.64
     tabel
    0.62
    たと
    0.62
    Act Density 0.046%

    No Known Activations