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

    Neuronpedia

    INDEX
    Explanations

    summary

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     предназначен
    0.85
    जिसे
    0.84
     previewBuilder
    0.82
     связан
    0.80
    ১০
    0.79
    须知
    0.78
    定義
    0.78
    hereafter
    0.75
    一条
    0.75
    wherein
    0.75
    POSITIVE LOGITS
    m
    0.91
    U
    0.89
    al
    0.88
    i
    0.87
    Ks
    0.85
    K
    0.84
     t
    0.84
    St
    0.83
    n
    0.83
    N
    0.83
    Act Density 0.433%

    No Known Activations