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

    Neuronpedia

    INDEX
    Explanations

    version declaration or metadata

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ki
    0.86
     skirt
    0.82
    গুলোতে
    0.76
    Find
    0.75
     penetrating
    0.74
    Different
    0.73
     Nut
    0.72
    های
    0.72
    வர்களின்
    0.72
     Carpathian
    0.72
    POSITIVE LOGITS
    ूर्त
    0.99
    ༅
    0.96
    䒠
    0.94
    䨐
    0.93
    ইংরেজি
    0.91
     recordó
    0.90
     só
    0.90
     书
    0.90
     precluded
    0.89
     apreciar
    0.88
    Act Density 0.004%

    No Known Activations