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

    Neuronpedia

    INDEX
    Explanations

    ai, app, io, com, art domains

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     clear
    0.72
     Gmail
    0.67
     ||
    0.67
     Correction
    0.66
     typical
    0.66
     ২০০
    0.65
     Clear
    0.65
     slice
    0.64
     transt
    0.64
     corrected
    0.64
    POSITIVE LOGITS
    io
    1.51
     io
    1.26
    IO
    1.16
    ai
    1.01
    xyz
    0.97
    AI
    0.96
    app
    0.94
    Ai
    0.92
    com
    0.91
    ío
    0.89
    Act Density 0.113%

    No Known Activations