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

    Neuronpedia

    INDEX
    Explanations

    deferred consideration

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     contrário
    0.71
    IST
    0.69
    ensure
    0.68
    식회사
    0.68
     그래도
    0.68
     marchio
    0.67
    iciaire
    0.66
    IMPLEMENT
    0.66
     contrario
    0.65
    ИТ
    0.65
    POSITIVE LOGITS
    কেন্ড
    0.84
     Hone
    0.80
     Aspects
    0.79
     outflow
    0.79
     in
    0.78
     Aster
    0.78
     ⚫
    0.77
     dismantling
    0.77
     Erosion
    0.76
     Vantage
    0.76
    Act Density 0.010%

    No Known Activations