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

    Neuronpedia

    INDEX
    Explanations

    algorithm concepts in code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     النش
    0.62
     pha
    0.62
     mixt
    0.62
     Laurel
    0.58
     windows
    0.58
    ционе
    0.58
     Cult
    0.57
     action
    0.56
    pect
    0.56
     surf
    0.56
    POSITIVE LOGITS
    算法
    2.02
     алгорит
    2.00
    Algorithm
    2.00
     Algorithm
    1.91
     Algorithms
    1.86
    Algorithms
    1.85
     algoritmo
    1.81
    algorithm
    1.80
     algorithm
    1.79
     algorith
    1.73
    Act Density 0.860%

    No Known Activations