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

    Neuronpedia

    INDEX
    Explanations

    proposed algorithms and frameworks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    arettes
    0.50
    热情
    0.50
    фициа
    0.48
     capitalism
    0.48
     sărb
    0.48
    შინ
    0.48
     fiasco
    0.47
    ब्लिक
    0.47
    툼
    0.47
     bureaucracy
    0.46
    POSITIVE LOGITS
     algorithms
    0.92
     framework
    0.88
     algorithm
    0.88
     proposed
    0.87
     Algorithms
    0.86
     Algorithm
    0.84
     computationally
    0.83
     computational
    0.81
    framework
    0.81
     Framework
    0.80
    Act Density 0.059%

    No Known Activations