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

    Neuronpedia

    INDEX
    Explanations

    latex code and tikz diagrams

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    خلي
    0.83
    umpulkan
    0.82
    udson
    0.76
    ooky
    0.75
    淔
    0.75
    渟
    0.74
    utable
    0.74
     Gardner
    0.73
    மி
    0.73
    ycled
    0.72
    POSITIVE LOGITS
     MEM
    0.70
    hna
    0.68
     vox
    0.65
    Mem
    0.64
    global
    0.64
     dese
    0.64
     kla
    0.63
     крае
    0.63
    해
    0.63
    Memory
    0.62
    Act Density 0.001%

    No Known Activations