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

    Neuronpedia

    INDEX
    Explanations

    roots

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    кам
    1.02
    тере
    0.97
    рена
    0.96
    ो
    0.84
    линд
    0.83
    рот
    0.82
    िन
    0.81
    купа
    0.80
    𝑑
    0.80
    انی
    0.79
    POSITIVE LOGITS
     serta
    0.98
    ↵↵
    0.88
    ↵
    0.85
     CVS
    0.85
     sowie
    0.84
    ↵↵↵
    0.81
     Internet
    0.79
     Power
    0.78
    )")
    0.77
     HDI
    0.75
    Act Density 0.000%

    No Known Activations