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

    Neuronpedia

    INDEX
    Explanations

    language models

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Best
    1.06
    best
    1.01
    Fake
    0.93
     yahoo
    0.90
    Buy
    0.88
    ebay
    0.88
     ebay
    0.87
     aaa
    0.86
     kafka
    0.86
    how
    0.85
    POSITIVE LOGITS
     L
    0.74
     R
    0.66
    models
    0.66
     ბ
    0.65
     C
    0.65
     modèles
    0.64
     vestiges
    0.63
     კ
    0.62
     Т
    0.61
     И
    0.61
    Act Density 0.000%

    No Known Activations