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

    Neuronpedia

    INDEX
    Explanations

    index and urls

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     paga
    0.77
     எங்க
    0.73
     шокола
    0.71
     chocolate
    0.69
    між
    0.68
     Moist
    0.68
     wet
    0.65
    Ե
    0.65
     towel
    0.64
     progression
    0.64
    POSITIVE LOGITS
    Indexer
    0.78
    索引
    0.77
    indexing
    0.76
    🔦
    0.73
     indexBuffer
    0.72
    indexer
    0.72
    Indexing
    0.71
    ighthouse
    0.69
     treb
    0.69
     tratan
    0.68
    Act Density 0.059%

    No Known Activations