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

    Neuronpedia

    INDEX
    Explanations

    your column identifier

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ,
    0.55
    s
    0.52
     Menschen
    0.51
    women
    0.50
    annual
    0.49
     joven
    0.49
     tending
    0.48
    ́
    0.48
     noch
    0.47
    econom
    0.46
    POSITIVE LOGITS
     middleware
    0.91
     initialise
    0.89
     encapsulate
    0.83
     initialize
    0.82
     instantiate
    0.82
     Initialize
    0.80
     初始化
    0.80
     recursively
    0.78
    初始化
    0.78
     asynchronously
    0.77
    Act Density 1.410%

    No Known Activations