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

    Neuronpedia

    INDEX
    Explanations

    impacts, determines, or dictates choices

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    执行
    0.54
     执行
    0.53
    nil
    0.51
    同步
    0.47
    创建
    0.46
    眽
    0.46
    পতি
    0.46
    î
    0.44
    悱
    0.44
    実行
    0.44
    POSITIVE LOGITS
     реб
    0.51
     appliances
    0.48
     decide
    0.45
    န္
    0.44
     заяв
    0.44
     lefty
    0.44
     काळात
    0.44
     божомолу
    0.43
    Brock
    0.43
     selectable
    0.43
    Act Density 0.001%

    No Known Activations