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

    Neuronpedia

    INDEX
    Explanations

    conservation and scheduling

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     よる
    0.45
     suis
    0.41
     dili
    0.41
    𝓢
    0.41
     preoccupied
    0.40
     diluted
    0.40
    ırmaya
    0.39
     ocup
    0.39
     jsem
    0.39
     <%
    0.39
    POSITIVE LOGITS
    控制
    0.38
     контро
    0.38
    Conserv
    0.37
    祹
    0.36
    趄
    0.36
     Conservation
    0.35
    scheduling
    0.35
     Heat
    0.35
    換
    0.34
    trop
    0.34
    Act Density 0.000%

    No Known Activations